Abstract

A good post processing module is an indispensable part of an OCR pipeline. In this paper, we propose a novel method for error detection in Indian language OCR output. Our solution uses a recurrent neural network ( RNN ) for classification of a word as an error or not. We propose a generic error detection method and demonstrate its effectiveness on four popular Indian languages. We divide the words into their constituent aksharas and use their bigram and trigram level information to build a feature representation. In order to train the classifier on incorrect words, we use the mis-recognized words in the output of the OCR . In addition to RNN , we also explore the effectiveness of a generative model such as GMM for our task and demonstrate an improved performance by combining both the approaches. We tested our method on four popular Indian languages and report an average error detection performance above 80%.

Abstract

Egocentric videos are characterized by their ability to have the first person view. With the popularity of Google Glass and GoPro, use of egocentric videos is on the rise. With the substantial increase in the number of egocentric videos, the value and utility of recognizing actions of the wearer in such videos has also thus increased. Unstructured movement of the camera due to natural head motion of the wearer causes sharp changes in the visual field of the egocentric camera causing many standard third person action recognition techniques to perform poorly on such videos. Objects present in the scene and hand gestures of the wearer are the most important cues for first person action recognition but are difficult to segment and recognize in an egocentric video. We propose a novel representation of the first person actions derived from feature trajectories. The features are simple to compute using standard point tracking and do not assume segmentation of hand/objects or recognizing object or hand pose unlike in many previous approaches. We train a bag of words classifier with the proposed features and report a performance improvement of more than 11% on publicly available datasets. Although not designed for the particular case, we show that our technique can also recognize wearer's actions when hands or objects are not visible.

Abstract

Transgender face recognition is gaining increasing attention in the face recognition community because ofits potential in real life applications. Despite extensive progress in traditional face recognition domain, it is very challenging to recognize faces under transgender setting.The gender transformation results in significant face variations, both in shape and texture gradually over time. This introduces additional complexities to existing face recognition algorithms to achieve a reliable performance. In this paper, we present a novel framework that incorporates appearance factor and a transformation factor caused due to Hormone Replacement Therapy (HRT) for recognition.To this extent, we employ the Hidden Factor Analysis(HFA) to jointly model a face under therapy as a linear combination of appearance and transformation factors.This is based on the intuition that the appearance factor captures the features that are unaffected by the therapy and transformation factor captures the feature changes due to therapy. Extensive experiments carried out on publicly available HRT transgender face database shows the efficacy of the proposed scheme with a recognition accuracy of82.36%

Abstract

We present a practical solution for generating 360◦stereo panoramic videos using a single camera. Current approaches either use a moving camera that captures multiple images of a scene, which are then stitched together to form the final panorama, or use multiple cameras that are synchronized. A moving camera limits the solution to static scenes, while multi-camera solutions require dedicated calibrated setups. Our approach improves upon the existing solutions in two significant ways: It solves the problem using a single camera, thus minimizing the calibration problem and providing us the ability to convert any digital camera into a panoramic stereo capture device. It captures all the light rays required for stereo panoramas in a single frame using a compact custom designed mirror, thus making the design practical to manufacture and easier to use. We analyze several properties of the design as well as present panoramic stereo and depth estimation results.

Abstract

Fine-grained classification is an extremely challenging problem in computer vision, compounded by subtle differences in shape, pose, illumination and appearance. While convolutional neural networks have become the versatile jack-of-all-trades tool in modern computer vision, approaches for fine-grained recognition still rely on localization of keypoints and parts to learn discriminative features for recognition. In order to achieve this, most approaches use a localization module and subsequently learn classifiers for the inferred locations,thus necessitating large amounts of manual annotations for bounding boxes and key points. In order to tackle this problem,we aim to leverage the (taxonomic and/or semantic) relationships present among fine-grained classes. The ontology tree is a free source of labels that can be used as auxiliary tasks to train a multi-task loss. Additional tasks can act as regularizers, and increase the generalization capabilities of the network. Multiple tasks try to take the network in diverging directions, and the network has to reach a common minimum by adapting and learning features common to all tasks in its shared layers.We train a multi-task network using auxiliary tasks extracted from taxonomical or semantic hierarchies, using a novel method to update task-wise learning rates to ensure that the related tasks aid and unrelated tasks does not hamper performance on the primary task. Experiments on the popular CUB-200-2011 dataset show that employing super-classes in an end-to-end model improves performance, compared to methods employing additional expensive annotations such as key points and bounding boxes and/or using multi-stage pipelines.

Abstract

In computer vision, many active illumination techniques em-ploy Projector-Camera systems to extract useful information from the scenes. Known illumination patterns are projected onto the scene and their deformations in the captured images are then analyzed. We observe that the local frequencies in the captured pattern for the mirror-like surfaces is different from the projected pattern. This property allows us to design a custom Projector-Camera system to segment mirror-like surfaces by analyzing the local frequencies in the captured images. The system projects a sinusoidal pattern and capture the images from projector’s point of view. We present segmentation results for the scenes including multiple reflections and inter-reflections from the mirror-like sur-faces. The method can further be used in the separation of direct and global components for the mirror-like surfaces by illuminating the non-mirror-like objects separately. We show how our method is also useful for accurate estimation of shape of the non-mirror-like regions in the presence of mirror-like regions in a scene.

Abstract

The widespread popularity of the computer networks has triggered concerns about information security. Password-based user authentication with key agreement protocols have drawn attentions since it provides proper authentication of a user before granting access right to services, and then ensure secure communication over insecure channels. Recently, Lee et al. pointed out different security flaws on Tsaur et al.’s multi-server user authentication protocol, and they further proposed an extended chaotic maps-based user authentication with key agreement protocol for multi-server environments. However, we observed that Lee et al.’s protocol has some functionality and security flaws, i.e., it is inefficient in detection of unauthorized login and it does not support password change mechanism. Besides, their protocol is vulnerable to registration center spoofing attack and server spoofing attack. In order to remedy the aforementioned flaws, we proposed a novel chaotic maps-based user authentication with key agreement protocol for multi-server environments. The proposed protocol is provably secure in the random oracle model under the chaotic-maps based computational Diffie-Hellman assumption. In addition, we analyzed our protocol using BAN logic model. We also compared our protocol with Lee et al.’s protocol in aspects of computation cost, functionalities and securities.

Abstract

Authentication protocol plays an important role in the short-range wireless communications for the Near Field Communication (NFC) technology. Due to the shared nature of wireless communication networks, there are several kinds of security vulnerabilities. Recently, a pseudonym-based NFC protocol (PBNFCP) has been proposed to withstand the security pitfalls found in the existing conditional privacy preserving security protocol (CPPNFC). However, this paper further analyzes PBNFCP and shows that it still fails to prevent the claimed security properties, such as impersonation attacks against an adversary, who is a malicious registered user having a valid pseudonym and corresponding private key. In order to overcome these security drawbacks, this paper proposes a secure and efficient authentication protocol (SEAP) for NFC applications using lifetime-based pseudonyms. The proposed SEAP is simulated for the formal security verification using the widely-accepted AVISPA (Automated Validation of Internet Security Protocols and Applications) tool. The simulation results show that SEAP is secure. The rigorous security and performance analysis shows that the proposed SEAP is secure and efficient as compared to the related existing authentication protocols for NFC applications.

Abstract

A wireless medical sensor network (WMSN) is a professional application of the traditional wireless body area sensor networks in medicine. Using WMSNs, the parameters of patients’ vital signs can be gathered from the sensor nodes deployed on the body of the patients and accessed by the healthcare professionals by using a mobile device. Due to wireless communication, securing communication becomes a vital issue in WMSNs. Since the vital signs parameters are sensitive to the patients’ health status and these information must not be revealed to the others except the healthcare professionals, the protection of patients’ privacy becomes another key issue for WMSNs applications. Thus, user authentication with anonymity property is the most basic and commonly used method in order to resolve the security and privacy issues of WMSNs. He et al. presented a user authentication protocol for healthcare applications using WMSNs to protect the security and privacy problems. However, Li et al. showed that their scheme is incorrect in authentication and session key agreement phase, has no wrong password detection mechanism and is vulnerable to denial of service caused by password change with wrong password. In this paper, we review Li et al.’s scheme and show that their scheme is still vulnerable to privileged-insider attack, sensor node capture attack and fails to provide user anonymity property. Moreover, we find that He et al.’s scheme is still vulnerable to the same attacks as we find out in Li et al.’s scheme. In order to remedy the security weak-nesses found in both He et al.’s scheme and Li et al.’s scheme, we present a secure biometrics-based user authentication scheme in WMSNs using smart card. Through the rigorous formal and informal security analysis, we show that our scheme is secure against possible known attacks. In addition, we simulate our scheme using the most-widely accepted and used Automated Validation of Internet Security Protocols and Application stool and the simulation results reveal that our scheme is secure. Our scheme is also efficient in computation and communication as compared to He et al.’s scheme, Li et al.’sscheme and other related schemes.

Abstract

Rapid development of the wireless communication technology and low cost of sensing devices has accelerated the development of wireless sensor networks (WSNs). These types of networks have a wide range of applications including habitat monitoring, health monitoring, data acquisition in hazardous environmental conditions and military operations. Sensor nodes are resource constrained having limited communication range, battery and processing power. Sensor nodes are prone to failure and can be also physically captured by an adversary. One of the main concerns in WSNs is to provide security, especially in the cases where they are deployed for military applications and monitoring. Further, WSNs are prone to various attacks such as wormhole, sinkhole and blackhole attacks. A blackhole attack is a kind of denial of service attack, which is very difficult to detect and defend and such blackhole attack, if happens, affects the entire performance of the network. In addition, it causes high end-to-end delay and less throughput with less packet delivery ratio. The situation can be worst if multiple blackhole attacker nodes present in the network. As a result, detection and prevention of the blackhole attack becomes crucial in WSNs. In this paper, we aim to propose a new efficient group-based technique for the detection and prevention of multiple blackhole attacker nodes in WSNs. In our approach, the entire WSN is divided into several clusters and each cluster has a powerful high-end sensor node (called a cluster head), which is responsible for the detection of blackhole attacker nodes, if present, in that cluster. The proposed scheme achieves about 90 % detection rate and 3.75 % false positive rate, which are significantly better than the existing related schemes. Furthermore, our scheme is efficient and thus, it is very appropriate for practical applications in WSNs.