CVIT Projects

Security and Privacy of Visual Data

With a rapid development and acceptablity of computer vision based systems in one's daily life, securing of the visual data has become imperative. Security issues in computer vision primarily originates from the storage, distribution and processing of the personal data, whereas privacy concerns with tracking down of the user's activity. The current methods of securing an online protocol is to apply a cryptographic layer on top of an existing processing modules, thus securing the data against unauthorised third party access. However, this is often not enough to ensure the complete security of the user's privileged information. Through this work we address specific security and privacy concerns of the visual data. We propose application specific, computationally efficient and provably secure computer vision algorithms for the encrypted domain. More specifically we address the following issues:

Efficacy: Security should not be at the cost of accuracy.
Efficiency: Encryption/Decryption is computationaly expensive. Secure algorithms should be practical.
Domain Knowledge: Domain specific algorithms will be more efficient than generic solutions such as SMC.
Security: Algorithms need to be provably-secure and meet futuristic requirements.

Resources: POSTER PRESENTATION

Private Content Based Image Retrieval

PCBIR Icon For content level access, very often database needs the query as a sample image. However, the image may contain private information and hence the user does not wish to reveal the image to the database. Private Content Based Image Retrieval (PCBIR) deals with retrieving similar images from an image database without revealing the content of the query image. not even to the database server. We propose algorithms for PCBIR, when the database is indexed using hierarchical index structure or hash based indexing scheme. Experiments are conducted on real datasets with popular features and state of the art data structures. It is observed that specialty and subjectivity of image retrieval (unlike SQL queries to a relational database) enables in computationally efficient yet private solutions.

[Project Homepage]

Blind Authentication: A Crypto-Biometric Verification Protocol

Biometric authentication provides a secure, non-repudiable and convenient method for identity verification. Hence they are ideal to be deployed in both high security as well as remote authentication applications. However, the assertions on security and non-repudiation are valid only if the integrity of the overall system is maintained. A hacker who gains physical or remote access to the system can read or modify the stored templates and successfully pose as or deny access to legitimate users. We propose a secure biometric authentication protocol over public networks using asymmetric encryption, which captures the advantages of biometric authentication as well as the security of public key cryptography. Blind Authentication provides non-repudiable identity verification, while not revealing any additional information about the user to the server or vice versa.

Privacy Preserving Video Surveillance

Widespread use of surveillance cameras in offices and other business establishments, pose a significant threat to the privacy of the employees and visitors. The challenge of introducing privacy and security in such a practical surveillance system has been stifled by the enormous computational and communication overhead required by the solutions. In this work, we propose to utilize some of the inherent properties of the image data to enable efficient and provably secure surveillance algorithms. Our method enables distributed secure processing and storage, while retaining the ability to reconstruct the original data in case of a legal requirement. Our proposed paradigm is highly secure and extreamly fast over the traditional SMC, making privacy preserving surveillance practical.

[Project Homepage]

Fast and Secure Video Encryption

In the recent years, there has been tremendous growth in the areas like networking, digital multimedia, etc., which made multimedia distribution much simpler, for many fascinating applications. So, Businesses and other organizations are now able to perform real-time audio and video conferencing, even over a non-dedicated channel. An eavesdropper can conveniently intercept and capture the sensitive and valuable multimedia content travelling in a public channel. Hence, multimedia security is needed for commerce. This work is focused on proposing new techniques for the security of the video data especially for real-time applications. The major challenges in developing an ideal video encryption algorithm are providing good security against different types of security attacks, no overhead on the MPEG compression process and less encryption time in order to support real-time transfer of the videos. Brief project details.

Related Publications

Maneesh Upmanyu, Anoop M. Namboodiri, K. Srinathan and C. V. Jawahar - Efficient Biometric Verification in Encrypted Domain Proceedings of the 3rd International Conference on Biometrics (ICB 2009), pp. 899-908, June . 2-5, 2009, Alghero, Italy. [PDF]
Maneesh Upmanyu, Anoop M. Namboodiri, K. Srinathan and C.V. Jawahar - Efficient Privacy Preserving Video Surveillance Poceedings of the 12th International Conference on Computer Vision (ICCV), 2009, Kyoto, Japan [PDF]
C. Narsimha Raju, Gangula Umadevi, Kannan Srinathan and C. V. Jawahar - Fast and Secure Real-Time Video Encryption IEEE Sixth Indian Conference on Computer Vision, Graphics & Image Processing (ICVGIP 2008), pp. 257-264, 16-19 Dec,2008, Bhubaneswar, India. [PDF]
C. Narsimha Raju, UmaDevi Ganugula, Srinathan Kannan and C.V. Jawahar - A Novel Video Encryption Technique Based on Secret Sharing Proc. of IEEE International Conference on Image Processing(ICIP),Oct 12-15, 2008,San Diego, USA. [PDF]
Shashank J, Kowshik P, Kannan Srinathan and C.V. Jawahar - Private Content Based Image Retrieval Proceedings of IEEE computer society conference on Computer Vision and Pattern Recognition (CVPR) 2008, Egan Convention Center, Anchorage, Alaska, June 24-26, 2008. [PDF]
C. Narsimha Raju, Kannan Srinathan and C. V. Jawahar - A Real-Time Video Encryption Exploiting the Distribution of the DCT coefficients IEEE TENCON, November 18-21,2008, Hyderabad, India. [PDF]

Associated People

Dr. C. V. Jawahar
Maneesh Upmanyu
Kowshik Palivela

Dr. Anoop M. Namboodiri
Narsimha Raju
Shashank Jagarlamudi

Dr. Kannan Srinathan

Projected Texture for 3D Object Recognition

Introduction

Three dimensional object are characterized by their shape, which can be thought of as the variation in depth over the object, from a particular view point. These variations could be deterministic as in the case of rigid objects or stochastic for surfaces containing a 3D texture. These depth variations are lost during the process of imaging and what remains is the intensity variations that are induced by the shape and lighting, as well as focus variations. Algorithms that utilize 3D shape for classification tries to recover the lost 3D information from the intensity or focus variations or using additional cues from multiple images, structured lighting, etc. This process is computationally intensive and error prone. Once the depth information is estimated, one needs to characterize the object using shape descriptors for the purpose of classification.

Image-based classification algorithms tries to characterize the intensity variations of the image of the object for recognition. As we noted, the intensity variations are affected by the illumination and pose of the object. The attempt of such algorithms is to derive descriptors that are invariant to the changes in lighting and pose. Although image based classification algorithms are more efficient and robust, their classification power is limited as the 3D information is lost during the imaging process.

pattern shift1 We propose the use of structured lighting patterns, which we refer to as projected texture, for the purpose of object recognition. The depth variations of the object induces deformations in the projected texture, and these deformations encode the shape information. The primary idea is to view the deformation pattern as a characteristic property of the object and use it directly for classification instead of trying to recover the shape explicitly. To achieve this we need to use an appropriate projection pattern and derive features that sufficiently characterize the deformations. The patterns required could be quite different depending on the nature of object shape and its variation across objects.

3D Texture Classification

A feature "Normalized Histogram of Derivative of Gradients (NHoGD) is proposed to capture deformation statistic for parallel projection patterns.

Gradient directions in images are the directions of maximal intensity variation. In our scenario, the gradient directions can indicate the direction of the projected lines. As the lines get deformed with surface height variations, we compute the differential of the gradient directions in both x and y axes to measure the rate at which the surface height varies. The derivatives of gradients are computed at each pixel in the image, and the texture is characterized by a Histogram of the Derivatives of Gradients (HoDG). The gradient derivative histogram is a good indicator of the nature of surface undulations in a 3D texture. For classification, we treat the histogram as a feature vector to compare two 3D textures. As the distance computation involves comparing corresponding bins from different images, we normalize the counts in each bin of the histogram across all the samples in the training set. This normalization allows us to treat the distance between corresponding bins between histograms, equally, and hence employ the Euclidean distance for comparison of histograms. The Normalized histograms, or NHoDG is a simple but extremely effective feature for discriminating between different texture classes. Figure on right illustrates the computation of the NHoDG feature from a simple image with bell shaped intensity variation.

Category Recognition for Rigid Objects

The primary concerns in developing a representation for object category is that the description should be invariant to both shape and pose of the object. Note that the use of projected patterns allows us to avoid object texture, and concentrate only on its shape. Approaches such as ’bag of words’ computed from interest points have been successfully employed for image based object category recognition.

Our approach is similar in spirit to achieve pose invariance. We learn the class of local deformations that are possible for each category of objects by creating a codebook of such deformations from a training set. Each object is then represented as a histogram of local deformations based on the codebook. Figure on left illustrates the computation of the feature vector from a scene with projected texture. There are two primary concerns to be addressed while developing a parts based shape representation: The location of points from which the local shape descriptor is computed is important to achieve position invariance. In image based algorithms, the patches are localized by using an interest operator that is computed from object texture or edges. However, in our case the primary objective is to avoid using texture information and concentrate on the shape information provided by the projected texture. Hence we choose to use a set of overlapping windows that covers the whole scene for computation of local deformations. Our representation based on the codebook allows us to concentrate on the object deformation for recognition. The description of the local deformations should be sufficient to distinguish between various local surface shapes within the class of objects. The feature vector used exploits the periodic nature of projected patterns. Since Fourier representation is an effective descriptor for periodic signals, and since we are interested in the nature of deformation and not its exact location, we compute magnitude or the absolute value of the Fourier coefficients (AFC) corresponding to each of the window patch as our feature vector. To make comparisons in a Euclidean space for effective, we use a logarithmic representation of these coefficients (LAFC). We show that this simple Fourier magnitude based representation of the patches can effectively achieve the discriminative power that we seek. The feature extraction process proceeds as follows: The images in the training set are divided into a set of overlapping windows of size 20×20 (decided experimentally). Each window is then represented using the magnitude of Fourier representation in logarithmic scale. This results in a 200 dimensional feature vector (due to symmetry of Fourier representation) for each window. A K-means clustering of windows in this feature space allows us to identify the dominant pattern deformations, which forms a codebook

Recognition of Aligned Deterministic shapes

We have taken the example of hand geometry based person authentication for demonstrating our approach. We have collected dataset of 181 user with peg based alignment. We divided the hand image into a set of non-overlapping sub-windows, and compute the local textural characteristics of each window using a filter bank of 24 Gabor filters with 8 orientations and 3 scales (or frequencies).