The 2014 International Conference on Signal Propagation and Computer Technology (ICSPCT) was held 12-13 July 2014 at Ajmer, India. The technical program of IEEE ICSPCT 2014 consists of 21 Session’s: 13 Signal Propagation, 9 Computer Technology, and 2 Engineering Professionals. The organizers received more than 650 paper submissions from 10 countries, of which 155 papers were accepted. The Science of Security-related papers are cited here.
Prakash, G.L.; Prateek, M.; Singh, I., "Data Encryption And Decryption Algorithms Using Key Rotations For Data Security In Cloud System," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on , vol., no., pp.624,629, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884895 Outsourcing the data in cloud computing is exponentially generating to scale up the hardware and software resources. How to protect the outsourced sensitive data as a service is becomes a major data security challenge in cloud computing. To address these data security challenges, we propose an efficient data encryption to encrypt sensitive data before sending to the cloud server. This exploits the block level data encryption using 256 bit symmetric key with rotation. In addition, data users can reconstruct the requested data from cloud server using shared secret key. We analyze the privacy protection of outsourced data using experiment is carried out on the repository of text files with variable size. The security and performance analysis shows that the proposed method is highly efficient than existing methods performance.
Keywords: {cloud computing; cryptography; data protection; outsourcing; block level data encryption; cloud computing; cloud server; data decryption algorithms; data outsourcing; data security; hardware resources; key rotations; performance analysis; privacy protection; shared secret key; software resources; text files; variable size; Algorithm design and analysis; Computational modeling; Encoding; Encryption; Servers; Software; Data Block; Decryption; Encryption; Key Rotation; Outsource; Security (ID#: 14-3366)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884895&isnumber=6884878
Duhan, N.; Saneja, B., "A Two Tier Defense Against SQL Injection," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.415,420, 12-13 July 2014
doi: 10.1109/ICSPCT.2014.6884906 In recent years with increase in ubiquity and popularity of web based applications, information systems are frequently migrated to the web, which will jeopardize security and privacy of the users. One of the most easiest and hazardous security attacks confronted by these systems is SQL injection attacks (SQLIAs). SQL injection attack is a method that can insert any malevolent query into the original query statement. In this paper, we demonstrate an efficient approach for Securing Web Application from SQL injection, which incorporates the combination of client side validation and identity based cryptography. To affirm the technique we examine it on some prototype web applications generated by web developer tools which ensure that our approach is secure and efficient and also hypothesis testing is done to validate the results.
Keywords: Internet; SQL; client-server systems; cryptography; data privacy; SQL injection attacks; Web based applications; Web developer tools; client side validation; hazardous security attacks; identity based cryptography; information systems; malevolent query; original query statement; two-tier defense; user privacy; user security; Cryptography; Educational institutions; IP networks ;Information filters; Libraries; Injection attack; SQL Injection; SQL Query; SQLIAs; Web application (ID#: 14-3367)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884906&isnumber=6884878
Chatterjee, S.; Gupta, A.K.; Mahor, V.K.; Sarmah, T., "An Efficient Fine Grained Access Control Scheme Based On Attributes For Enterprise Class Applications," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.273,278, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884907 Fine-grained access control is used to assign unique access privilege to a particular user for accessing any particular enterprise class application for which he/she is authorized. The existing mechanisms for restricting access of users to resources are mostly static and not fine grained. Those are not well-suited for the enterprise class applications where information access is dynamic and ad-hoc in nature. As a result, we need to design an effective fine grained access as well as authorization control scheme to control access to objects by evaluating rules against the set of attributes given both for the users and application objects. In this paper, we propose a new fine grained access and authorization control scheme based on attributes which is suitable for large enterprise class applications. The strengths of our proposed scheme based on attributes are that it provides fine grained access control with its authorization architecture and policy formulation based on attribute based access tree. In comparison with the role based access control (RBAC) approach, in this scenario there is no need to explicitly define any roles. Here, based on user access tree any user can get access to any particular application with full granularity.
Keywords: authorisation; business data processing; RBAC; attribute based access tree; authorization architecture; authorization control scheme; efficient fine grained access control scheme; enterprise class applications; policy formulation; role based access control; unique access privilege; user access tree; Cryptography; Logic gates; Safety (ID#: 14-3368)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884907&isnumber=6884878
Sanadhya, S.; Agrawal, N.; Singh, S., "Pheromone Base Swarm Approach For Detecting Articulation User Node In Social Networking," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.461,465, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884910 Modern world is living in the `aeon' of virtual community, where people connect to each other through any kind of relationship. Social networking is platform where people share emotions, activities, area of interest etc. Communities in social network are deployed in user nodes with connecting people, it may seem that there is some user which is common among many communities. These user node is a kind of `social articulation points (SAP)' which is like a bridge between communities. In this paper with the help of `ant colony optimization' (ACO) we are proposing `pheromone based swarm approach for articulation user' (PSAP) to find articulation user point in a social network. ACO is meta-heuristic which helps to solve combinational problems such as TSP, Graph color, job shop Network routing, machine learning etc. Hence social networking may be a new platform with ant colony optimization, to solve complex task in social phenomena.
Keywords: {ant colony optimisation; combinatorial mathematics; social sciences; ACO; PSAP; SAP; TSP; ant colony optimization; articulation user node detection; combinational problems ;graph color; job shop network routing; machine learning; meta-heuristic; pheromone base swarm approach; social articulation points; social networking; social phenomena; user nodes; virtual community; Cities and towns; Context; Instruments; Signal processing algorithms; ACO; SAP; Swarm-Intelligence; user rank matrices (ID#: 14-3369)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884910&isnumber=6884878
Singh, B.; Singh, D.; Singh, G.; Sharma, N.; Sibbal, V., "Motion Detection For Video Surveillance," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.578,584, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884919 Motion detection is one of the key techniques for automatic video analysis to extract crucial information from scenes in video surveillance systems. This paper presents a new algorithm for MOtion DEtection (MODE) which is independent of illumination variations, bootstrapping, dynamic variations and noise problems. MODE is pixel based non-parametric method which requires only one frame to construct the model. The foreground/background detection starts from second frame onwards. It employs new object tracking method which detects and remove ghost objects rapidly while preserving abandon objects from decomposing into background. The algorithm is tested on public available video datasets consisting of challenging scenarios by using only one set of parameters and proved to outperform other state-of-art motion detection techniques.
Keywords: feature extraction; motion estimation; object tracking; video surveillance; MODE; automatic video analysis; bootstrapping; dynamic variations; foreground-background detection; illumination variations; information extraction; motion detection; noise problems; object tracking method; state-of-art motion detection techniques; video datasets; video surveillance systems; Computational modeling; Training; Uncertainty; Background Subtraction; Background modelling; Motion Detection; Video Surveillance (ID#: 14-3370)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884919&isnumber=6884878
Mewara, B.; Bairwa, S.; Gajrani, J., "Browser's Defenses Against Reflected Cross-Site Scripting Attacks," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on , vol., no., pp.662,667, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884928 Due to the frequent usage of online web applications for various day-to-day activities, web applications are becoming most suitable target for attackers. Cross-Site Scripting also known as XSS attack, one of the most prominent defacing web based attack which can lead to compromise of whole browser rather than just the actual web application, from which attack has originated. Securing web applications using server side solutions is not profitable as developers are not necessarily security aware. Therefore, browser vendors have tried to evolve client side filters to defend against these attacks. This paper shows that even the foremost prevailing XSS filters deployed by latest versions of most widely used web browsers do not provide appropriate defense. We evaluate three browsers - Internet Explorer 11, Google Chrome 32, and Mozilla Firefox 27 for reflected XSS attack against different type of vulnerabilities. We find that none of above is completely able to defend against all possible type of reflected XSS vulnerabilities. Further, we evaluate Firefox after installing an add-on named XSS-Me, which is widely used for testing the reflected XSS vulnerabilities. Experimental results show that this client side solution can shield against greater percentage of vulnerabilities than other browsers. It is witnessed to be more propitious if this add-on is integrated inside the browser instead being enforced as an extension.
Keywords: online front-ends; security of data; Google Chrome 32;Internet Explorer 11; Mozilla Firefox 27;Web based attack; Web browsers; XSS attack; XSS filters; XSS-Me; online Web applications; reflected cross-site scripting attacks; Browsers; Security; Thyristors; JavaScript; Reflected XSS;XSS-Me; attacker; bypass; exploit; filter (ID#: 14-3371)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884928&isnumber=6884878
Sinha, R.; Uppal, D.; Singh, D.; Rathi, R., "Clickjacking: Existing Defenses And Some Novel Approaches," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.396,401, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884934 With the growth of information technology, World Wide Web is experiencing a rapid increase in online social networks' users. A serious threat to the integrity of these users' data which has come into picture these days is Clickjacking. Many server side and client side defense mechanisms are available for clickjacking but many attackers are still exploiting popular online social networks like Facebook and Twitter so that a user clicks on a spam link and it leads to unwanted posts flooding on his Facebook wall, from which arises the need of a powerful methodology at tester, host and user levels to assuage clickjacking. This paper aims at discussing various tools, techniques and methods available to detect, prevent or reduce clickjacking attacks along with the extent of usefulness and shortcoming of each approach. Later, we have summarized the results and provided an analysis of what needs to be done in the field of web security to encounter and remove clickjacking from the host as well as the developer side. Lastly, we have tested and suggested on how clickjacking defenses can be improved at server side and during development.
Keywords: security of data; social networking (online);Facebook; Twitter; Web security; World Wide Web; clickjacking; information technology; online social networks; spam link; user data integrity; Browsers; Clickjacking; aspect oriented programming; framebusting; iframe; likejacking; user interface randomization; user interface redressing (ID#: 14-3372)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884934&isnumber=6884878
Vamsi, P.R.; Kant, K., "Sybil Attack Detection Using Sequential Hypothesis Testing in Wireless Sensor Networks," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.698,702, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884945 Sybil attack poses a serious threat to geographic routing. In this attack, a malicious node attempts to broadcast incorrect location information, identity and secret key information. A Sybil node can tamper its neighboring nodes for the purpose of converting them as malicious. As the amount of Sybil nodes increase in the network, the network traffic will seriously affect and the data packets will never reach to their destinations. To address this problem, researchers have proposed several schemes to detect Sybil attacks. However, most of these schemes assume costly setup such as the use of relay nodes or use of expensive devices and expensive encryption methods to verify the location information. In this paper, the authors present a method to detect Sybil attacks using Sequential Hypothesis Testing. The proposed method has been examined using a Greedy Perimeter Stateless Routing (GPSR) protocol with analysis and simulation. The simulation results demonstrate that the proposed method is robust against detecting Sybil attacks.
Keywords: {network theory (graphs);routing protocols; statistical testing; telecommunication security; wireless sensor networks; GPSR protocol; Sybil attack detection; encryption methods; geographic routing ;greedy perimeter stateless routing; location information; malicious node; network traffic; sequential hypothesis testing; wireless sensor networks; Acoustics; Actuators; Bandwidth; IEEE 802.11 Standards; Optimization; Robustness; Wireless sensor networks; Sequential hypothesis testing; Sybil attack; geographic routing; wireless sensor networks (ID#: 14-3373)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884945&isnumber=6884878
Agarwal, A.K.; Srivastava, D.K., "Ancient Kaṭapayādi System Sanskrit Encryption Technique Unified," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.279,282, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884947 Computers today, generate enormous amount of data/information with each moment passing by. With the production of such huge amount of information comes its indispensable part of information security. Encryption Algorithms today drastically increase the file size. Hence the secure transmission of data requires extra bandwidth. Here in this paper we propose a system AKS - SETU, which is also the abbreviation to the title of this paper. Using the ancient technique of encryption from Sanskrit, AKS - SETU not only encrypts the information but also attempts on decreasing of the file size. AKS - SETU performs Sanskrit encryption, which we propose to be termed as Sanscryption.
Keywords: cryptography; natural language processing; AKS-SETU; Sanscryption; ancient Kaṭapaya̅di system Sanskrit encryption technique unified; encryption algorithms; file size; information security; secure data transmission; Barium; Cryptography; Electronic publishing; Encyclopedias; Internet; Encryption; Information security; Kaṭpayādi system; Sanscryption; Sanskrit (ID#: 14-3374)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884947&isnumber=6884878
Kulkarni, P.; Kulkarni, S.; Mulange, S.; Dand, A.; Cheeran, A.N., "Speech Recognition Using Wavelet Packets, Neural Networks and Support Vector Machines," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.451,455, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884949 This research article presents two different methods for extracting features for speech recognition. Based on the time-frequency, multi-resolution property of wavelet transform, the input speech signal is decomposed into various frequency channels. In the first method, the energies of the different levels obtained after applying wavelet packet decomposition instead of Discrete Fourier Transforms in the classical Mel-Frequency Cepstral Coefficients (MFCC) procedure, make the feature set. These feature sets are compared to the results from MFCC. And in the second method, a feature set is obtained by concatenating different levels, which carry significant information, obtained after wavelet packet decomposition of the signal. The feature extraction from the wavelet transform of the original signals adds more speech features from the approximation and detail components of these signals which assist in achieving higher identification rates. For feature matching Artificial Neural Networks (ANN) and Support Vector Machines (SVM) are used as classifiers. Experimental results show that the proposed methods improve the recognition rates.
Keywords: feature extraction; neural nets; speech recognition; support vector machines; time-frequency analysis; wavelet transforms; ANN;MFCC procedure; SVM; artificial neural networks; feature extraction; frequency channels; input speech signal decomposition; mel-frequency cepstral coefficients; multiresolution property; speech recognition; support vector machines; time-frequency property; wavelet packet decomposition; wavelet packets; wavelet transform; Artificial neural networks; Mel frequency cepstral coefficient; Speech recognition; Time-frequency analysis; Artificial Neural Networks; Feature Extraction; Support Vector Machines; Wavelet Packet Transform (ID#: 14-3375)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884949&isnumber=6884878
Gupta, M.K.; Govil, M.C.; Singh, G., "An Approach To Minimize False Positive In SQLI Vulnerabilities Detection Techniques Through Data Mining," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.407,410, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884962 Dependence on web applications is increasing very rapidly in recent time for social communications, health problem, financial transaction and many other purposes. Unfortunately, the presence of security weaknesses in web applications allows malicious user's to exploit various security vulnerabilities and become the reason of their failure. Currently, SQL Injection (SQLI) attacks exploit most dangerous security vulnerabilities in various popular web applications i.e. eBay, Google, Facebook, Twitter etc. Research on taint based vulnerability detection has been quite intensive in the past decade. However, these techniques are not free from false positive and false negative results. In this paper, we propose an approach to minimize false positive in SQLI vulnerability detection techniques using data mining concepts. We have implemented a prototype tool for PHP, MySQL technologies and evaluated it on six real world applications and NIST Benchmarks. Our evaluation and comparison results show that proposed technique detects SQLI vulnerabilities with low percentage of false positives.
Keywords: Internet; SQL; data mining; security of data; social networking (online);software reliability; Facebook; Google; MySQL technology; PHP; SQL injection attack; SQLI vulnerability detection techniques; Twitter; data mining; eBay; false positive minimization; financial transaction; health problem; social communications; taint based vulnerability detection; Computers; Software; SQLI attack; SQLI vulnerability; false positive; input validation; sanitization; taint analysis (ID#: 14-3376)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884962&isnumber=6884878
Singh, A.K.; Kumar, A.; Nandi, G.C.; Chakroborty, P., "Expression Invariant Fragmented Face Recognition," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp. 184, 189, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884987 Fragmented face recognition suggests a new way to recognize human faces with most discriminative facial components such as: Eyes, Nose and Mouth. An experimental study has been performed on 360 different subjects which confirms that more than 80% features of the full face lies within these fragmented components. The framework intends to process each component independently in order to find its corresponding match score. Final score is obtained by calculating weighted majority voting (WMV) of each component matched score. Three different feature extraction techniques like Eigenfaces, Fisher-faces and Scale Invariant Feature Transform (SIFT) are applied on full faces and fragmented face database (ORL Dataset). It has been observed from the classification accuracy that the strength of local features (SIFT) leads to achieve an encouraging recognition rate for fragmented components whereas the global features (Eigenfaces, Fisherfaces) increases misclassification error rate. This selection of optimal subset of face minimizes the comparison time and it also retains the correct classification rate irrespective of changing in facial expression. A standard Japanese Female facial expression dataset (JAFFE) has been used to investigate the major impact on Fragmented feature components. we have obtained a promising classification accuracy of 98.7% with this proposed technique.
Keywords: face recognition; feature extraction; image classification; transforms; visual databases; Fisher-faces; JAFFE; ORL dataset; SIFT; WMV; classification accuracy; discriminative facial components; eigenfaces; expression invariant fragmented face recognition; eyes; feature extraction techniques; fragmented face database; global features; local features; mouth; nose; scale invariant feature transform; standard Japanese female facial expression dataset; weighted majority voting; Databases; Mouth; Nose; Principal component analysis; EigenFaces; Face Recognition; Facial Landmark Localization; FisherFaces; Scale Invariant Feature Transformation; Weighted Majority Voting (ID#: 14-3377)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884987&isnumber=6884878
Pandey, A.; Srivastava, S., "An Approach For Virtual Machine Image Security," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.616,623, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6884997 Cloud security being the main hindrance in adoption of cloud computing has some most vulnerable security concerns as: virtualization, data and storage. Here, to provide virtualization security, the components of virtualization (such as hypervisors, virtual machines, and virtual machine images) must be secured using some improvised security mechanisms. Amongst all components, Virtual machine images (VM images) are considered to be the fundamental of whole cloud security. Hence must be secured from every possible attack. In this paper, a security protocol is proposed to mainly protect the VM images from two of the possible attacks. One is the channel attack like man-in-the-middle attack (MITM attack) and second is the attack by a malicious executing environment. It is using a concept of symmetric key's component distribution providing an integrity based confidentiality and self-protection. This protection is based on an encapsulated mobile agent. Here one key component is generated and distributed in a secure manner and the other key component is derived by host platform itself using its own available resource configuration information. In order to verify the validity of this approach in overcoming different kind of security attacks, BAN logic based formal representation is presented.
Keywords: cloud computing; data protection; image processing; protocols; virtual machines; BAN logic based formal representation; MITM attack; VM images; channel attack; cloud computing; cloud security; encapsulated mobile agent; hypervisors; integrity based confidentiality; malicious executing environment; man-in-the-middle attack; resource configuration information; security attacks; security protocol; self-protection; symmetric key component distribution; virtual machine image security; virtualization security; Elasticity; Home appliances; Operating systems; Servers; Virtualization; BAN logic; cloud computing; mobile agent; self-protection approach; virtual machine image security (ID#: 14-3378)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6884997&isnumber=6884878
Sharma, M.; Chaudhary, A.; Mathuria, M.; Chaudhary, S.; Kumar, S., "An Efficient Approach For Privacy Preserving In Data Mining," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.244,249, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6885001 In many organizations large amount of data are collected. These data are sometimes used by the organizations for data mining tasks. However, the data collected may contain private or sensitive information which should be protected. Privacy protection is an important issue if we release data for the mining or sharing purpose. Privacy preserving data mining techniques allow publishing data for the mining purpose while at the same time preserve the private information of the individuals. Many techniques have been proposed for privacy preservation but they suffer from various types of attacks and information loss. In this paper we proposed an efficient approach for privacy preservation in data mining. Our technique protects the sensitive data with less information loss which increase data usability and also prevent the sensitive data for various types of attack. Data can also be reconstructed using our proposed technique.
Keywords: data mining; data protection; data mining; data usability; information loss; privacy preservation; privacy protection; sensitive data protection; Cancer; Cryptography; Databases; Human immunodeficiency virus; Irrigation; Data mining; K- anonymity; Privacy preserving; Quasi-identifier; Randomization; Sensitive data (ID#: 14-3379)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6885001&isnumber=6884878
Nandy, A.; Pathak, A.; Chakraborty, P.; Nandi, G.C., "Gait Identification Using Component Based Gait Energy Image Analysis," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.380,385, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6885005 In the modern era of computer vision technology, gait biometric trait increases the proliferation of human identification in video surveillance situation. This paper intends to discuss the robustness of gait identification irrespective of small fluctuation in subject's walking pattern. The Gait Energy Image (GEI) is computed on silhouette gait sequences obtained from OU-ISIR standard gait database. The advantage of working with GEI is to preserve the shape and motion information into a single averaged gait image with fewer dimensions. The three independent components such as head node, body torso and leg region are separated from subject's GEI in accordance to body segment ratio. The local biometric feature has been computed from the shape centroid to the boundary points of each segment. The normality testing of feature for each region of GEI body frame ascertains the discriminative power of each segment. The similarity measurement between gallery and probe gait energy image has been computed by cosine distance, correlation distance and Jaccard distance. The performance efficiency of different distance based metrics is measured by several error metrics.
Keywords: biometrics (access control); computer vision; gait analysis; image motion analysis; image recognition;image segmentation; video surveillance; GEI body frame region; Jaccard distance; OU-ISIR standard gait database; body segment ratio; body torso; component based gait energy image analysis; computer vision technology; correlation distance; cosine distance; discriminative power; distance based metrics; error metrics; gait biometric trait; gait identification; gallery image; human identification; independent components; leg region; local biometric feature; motion information; normality feature testing; performance efficiency; probe gait energy image; shape centroid; shape preserving; silhouette gait sequences; similarity measurement; single averaged gait image; subject walking pattern; video surveillance situation; Image segmentation; Indexes; Robot sensing systems; Standards; Body Centroid; Body Segmentation; Correlation Distance; Cosine Distance; Euclidean Distance; Gait Energy Image; Human Gait; Jaccard Distance; OU-ISIR Gait Database (ID#: 14-3380)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6885005&isnumber=6884878
Pande, D.; Sharma, C.; Upadhyaya, V., "Object Detection And Path Finding Using Monocular vision," Signal Propagation and Computer Technology (ICSPCT), 2014 International Conference on, pp.376,379, 12-13 July 2014. doi: 10.1109/ICSPCT.2014.6885028 This project consists of a prototype of an autonomous robot that picks up the desired object (red can) solely based on camera vision. A robotic clamp and a camera are mounted on it. All the information is transferred wirelessly up to distances of 100 ft. The processing of the image is done on an external computer using software like OpenCV, Python and Microsoft Visual Studio. Using samples and regression analysis, the distance of any pixel and the width of any object can be found. After obstacle detection, a suitable path is chosen. All movement is controlled by PIC microcontroller with the help of RF transmitter-receiver modules. It is best suited for non-textured, flat surfaces with little or no movement in the foreground.
Keywords: collision avoidance; microcontrollers; mobile robots; object detection; regression analysis; robot vision; Microsoft; OpenCV; PIC microcontroller; Python; RF transmitter-receiver modules; autonomous robot; camera vision; monocular vision; object detection; path finding; regression analysis; robotic clamp; visual studio; Clamps; I EEE 802.11 Standards; Portable computers; Radio frequency; Robots; Autonomous robot; Compute Vision; Image processing; Monocular Vision; Path Finding (ID#: 14-3381)
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6885028&isnumber=6884878
Note:
Articles listed on these pages have been found on publicly available internet pages and are cited with links to those pages. Some of the information included herein has been reprinted with permission from the authors or data repositories. Direct any requests via Email to SoS.Project (at) SecureDataBank.net for removal of the links or modifications to specific citations. Please include the ID# of the specific citation in your correspondence.