International Institute of Information Technology, Hyderabad

About: International Institute of Information Technology, Hyderabad is a education organization based out in Hyderabad, India. It is known for research contribution in the topics: Authentication & Internet security. The organization has 2048 authors who have published 3677 publications receiving 45319 citations. The organization is also known as: IIIT Hyderabad & International Institute of Information Technology (IIIT).

Currency Recognition on Mobile Phones

Abstract: In this paper, we present an application for recognizing currency bills using computer vision techniques, that can run on a low-end smartphone. The application runs on the device without the need for any remote server. It is intended for robust, practical use by the visually impaired. Though we use the paper bills of Indian National Rupee (I) as a working example, our method is generic and scalable to multiple domains including those beyond the currency bills. Our solution uses a visual Bag of Words (BoW) based method for recognition. To enable robust recognition in a cluttered environment, we first segment the bill from the background using an algorithm based on iterative graph cuts. We formulate the recognition problem as an instance retrieval task. This is an example of fine-grained instance retrieval that can run on mobile devices. We evaluate the performance on a set of images captured in diverse natural environments, and report an accuracy of 96.7% on 2584 images.

Deep Learning for Understanding Satellite Imagery: An Experimental Survey.

Abstract: Translating satellite imagery into maps requires intensive effort and time, especially leading to inaccurate maps of the affected regions during disaster and conflict. The combination of availability of recent datasets and advances in computer vision made through deep learning paved the way toward automated satellite image translation. To facilitate research in this direction, we introduce the Satellite Imagery Competition using a modified SpaceNet dataset. Participants had to come up with different segmentation models to detect positions of buildings on satellite images. In this work, we present five approaches based on improvements of U-Net and Mask R-Convolutional Neuronal Networks models, coupled with unique training adaptations using boosting algorithms, morphological filter, Conditional Random Fields and custom losses. The good results-as high as A P = 0.937 and A R = 0.959 -from these models demonstrate the feasibility of Deep Learning in automated satellite image annotation.

Neutral to Target Emotion Conversion Using Source and Suprasegmental Information

Abstract: This work uses instantaneous pitch and strength of excitation along with duration of syllable-like units as the parameters for emotion conversion. Instantaneous pitch and duration of the syllable-like units of the neutral speech are modified by the prosody modification of its linear prediction (LP) residual using the instants of significant excitation. The strength of excitation is modified by scaling the Hilbert envelope (HE) of the LP residual. The target emotion speech is then synthesized using the prosody and strength modified LP residual. The pitch, duration and strength modification factors for emotion conversion are derived using the syllable-like units of initial, middle and final regions from an emotion speech database having different speakers, texts and emotions. The effectiveness of the region wise modification of source and supra segmental features over the gross level modification is confirmed by the waveforms, spectrograms and subjective evaluations. Index Terms: Emotions, ZFF, strength of excitation, instantaneous pitch, duration

Robust Anonymous Mutual Authentication Scheme for n -Times Ubiquitous Mobile Cloud Computing Services

Abstract: In recent years, mobile computing has gained a huge popularity among mobile users (MUs). It basically combines the mobile devices with the cloud computing. By the means of on-demand self-service and extendibility, it can offer the infrastructures, platform, entertainments, and software services in a cloud to MUs through the mobile network. However, offering secure access to these services by preserving the privacy of the MU is indeed a challenge for any mobile cloud service provider. In this paper, we aim to propose a new robust anonymous mutual authentication scheme for mobile cloud environment. Through this scheme, both the MU and the service cloud need to prove their legitimacy, and it eventually helps the legitimate mobile cloud user to enjoy n times all the ubiquitous services in a secure and efficient way, where the value of n may differ based on the principal he/she has paid for. The security of the proposed scheme is thoroughly analyzed using both formal as well as informal security analysis. Furthermore, functionality and performance comparisons using the testbed simulation among the proposed scheme and other existing relevant schemes reveal that the proposed scheme outperforms other existing schemes.

Sparse matrix-matrix multiplication on modern architectures

Abstract: Sparse matrix-sparse/dense matrix multiplications, spgemm and csrmm, respectively, among other applications find usage in various matrix formulations of graph problems. Considering the difficulties in executing graph problems and the duality between graphs and matrices, computations such as spgemm and csrmm have recently caught the attention of HPC community. These computations pose challenges such as load balancing, irregular nature of the computation, and difficulty in predicting the output size. It is even more challenging when combined with the GPU architectural constraints such as memory accesses, limited shared memory, strict SIMD and thread execution. To address these challenges on a GPU, we evaluate three possible variations of matrix multiplication (Row-Column, Column-Row, Row-Row) and perform suitable optimizations targeted at sparse matrices. Our experiments indicate that the Row-Row formulation, which mostly outperforms the other formulations, is 3.5x faster on average compared to an optimized multi-core implementation in the Intel MKL library. We extend the Row-Row formulation to a CPU+GPU hybrid algorithm that simultaneously utilizes the CPU also. In this direction, we present heuristics to find the right amount of work division between the CPU and the GPU. Our hybrid row-row formulation of the spgemm operation performs 5.5x faster on average when compared to the optimized multi-core implementation in the Intel MKL library. Our experience indicates that it is difficult to identify right amount of work division between the CPU and the GPU. We therefore investigate a subclass of sparse matrices, band matrices, and present an analytical method to identify a good work division when multiplying two band matrices. Our GPU csrmm operation performs 2.5x faster on average when compared to a corresponding implementation in the cusparse library, which outperforms the Intel MKL library implementation.