P. K. Bora

A robust static hand gesture recognition system using geometry based normalizations and Krawtchouk moments

Static hand gesture recognition involves interpretation of hand shapes by a computer. This work addresses three main issues in developing a gesture interpretation system. They are (i) the separation of the hand from the forearm region, (ii) rotation normalization using the geometry of gestures and (iii) user and view independent gesture recognition. The gesture image comprising the hand and the forearm is detected through skin color detection and segmented to obtain a binary silhouette. A novel method based on the anthropometric measures of the hand is proposed for extracting the regions constituting the hand and the forearm. An efficient rotation normalization method that depends on the gesture geometry is devised for aligning the extracted hand. These normalized binary silhouettes are represented using the Krawtchouk moment features and classified using a minimum distance classifier. The Krawtchouk features are found to be robust to viewpoint changes and capable of achieving good recognition for a small number of training samples. Hence, these features exhibit user independence. The developed gesture recognition system is robust to similarity transformations and perspective distortions. It can be well realized for real-time implementation of gesture based applications.

A study on static hand gesture recognition using moments

Hand gesture recognition is one of the key techniques in developing user-friendly interfaces for human-computer interaction. Static hand gestures are the most essential facets of gesture recognition. View point invariance and user independence are among the important requirements for realizing a real time gesture recognition system. In this context, the geometric moments and the orthogonal moments namely the Zernike, Tchebichef and Krawtchouk moments are explored. The proposed system detects the hand region through skin color identification and obtains the binary silhouette. These images are normalized for rotation and scale changes. The moment features of the normalized hand gestures are classified using a minimum distance classifier. The classification results suggest that the Krawtchouk moment features are comparatively robust to view point changes and also exhibit user independence.

Feature Extraction from 2D Gesture Trajectory in Dynamic Hand Gesture Recognition

Vision-based hand gesture recognition is a popular research topic for human-machine interaction (HMI). We have earlier developed a model-based method for tracking hand motion in complex scene by using Hausdorff tracker. In this paper, we now propose to extract certain features from the gesture trajectory so as to identify the form of the trajectory. Thus, these features can be efficiently used for trajectory guided recognition/classification of hand gestures. Our experimental results show 95% of accuracy in identifying the forms of the gesture trajectories. This indicates that the trajectory features proposed in this paper are appropriate for defining a particular gesture trajectory

Illuminant colour based image forensics

Detecting forgery in digital images is one of the major research activities in the current time. We propose a method to find the forgery in digital images by exploiting colour mismatches among the objects in the image. While creating a composite image from a number of images, it becomes hard to match the colour of one object with reference to the other. In the proposed method, the colour mismatch is decided by estimating the illuminant colour of different objects in the image.

An efficient hardware implementation of DWT and IDWT

Real-time applications of discrete wavelet transform (DWT), like video and audio compression, necessitate fast computation of DWT. Full-custom VLSI devices have been used for fast, though expensive, implementations of DWT. Field-programmable gate array (FPGA) architectures offer economical but area-constrained implementation of DWT. The paper proposes an efficient FPGA architecture for DWT as well as inverse DWT (IDWT). Use of distributed arithmetic allows us to do without area-consuming multipliers in the present realization. The proposed architecture is modular and allows extension to any precision without much effect on the clock frequency. Simulation results have established that the proposed fast implementation scheme can produce high-quality reconstructed signals.

Electrocardiogram signal denoising using non-local wavelet transform domain filtering

Electrocardiogram (ECG) signals are usually corrupted by baseline wander, power-line interference, muscle noise etc. Numerous methods have been proposed to remove these noises. However, in case of wireless recording of the ECG signal it gets corrupted by the additive white Gaussian noise (AWGN). For the correct diagnosis, removal of AWGN from ECG signals becomes necessary as it affects the diagnostic features. The natural signals exhibit correlation among their samples and this property has been exploited in various signal restoration tasks. Motivated by that, in this study we propose a non-local wavelet transform domain ECG signal denoising method which exploits the correlations among both local and non-local samples of the signal. In the proposed method, the similar blocks of the samples are grouped in a matrix and then denoising is achieved by the shrinkage of its two-dimensional discrete wavelet transform coefficients. The experiments performed on a number of ECG signals show significant quantitative and qualitative improvements in denoising performance over the existing ECG signal denoising methods.

A Framework for Hand Gesture Recognition with Applications to Sign Language

Sign language is the most natural and expressive way for the hearing impaired. Because of this, automatic sign language recognition has long attracted vision researchers. It offers enhancement of communication capabilities for the speech and hearing impaired, promising improved social opportunities and integration. This paper describes a gesture recognition system which can recognize wide classes of hand gesture in a vision based setup. Experimental results demonstrate that our proposed recognition system can be used reliably in recognizing some signs of native Indian sign language

Assessing motion-coherency in video watermarking

Motion coherent watermarking has been recently proposed as a means to combat temporal frame averaging along the motion axis (MC-TFA). The fundamental idea consists in exploiting motion-compensation primitives to force a physcal point of the scene to always carry the same watermark sample wherever it is projected in the video. However, for a given watermarking system, there is no simple tool to assess whether the produced watermark is motion-coherent or not. Today, this assessment relies on a computationally expensive procedure, namely (i) embed a watermark, (ii) perform the MC-TFA attack, (iii) check for the presence of the watermark. Therefore, the goal of this article is to provide the community with an efficient and accurate oracle which reports whether a video sequence contains any non-motion coherent component or not. This is done in practice by looking at the statistics of the difference between a frame and a motion predicted version of it.

Wavelet weighted blood vessel distortion measure for retinal images

Abstract In this paper, a novel wavelet transform based blood vessel distortion measure (WBVDM) is proposed to assess the image quality of blood vessels in the processed retinal images. The wavelet analysis of retinal image shows that different wavelet subbands carry different information about the blood vessels. The WBVDM is defined as the sum of wavelet weighted root of the normalized mean square error of subbands expressed in percentage. The proposed WBVDM is compared with other wavelet based distortion measures such as wavelet mean square error(WMSE), Relative WMSE(Rel WMSE) and root of the normalized WMSE(RNWMSE). The results show that WBVDM performs better in capturing the blood vessel distortion. For distortion in clinically nonsignificant regions, the proposed WBVDM shows a low value of 1.1676 compared to a large mean square error value of 7.9909. The evaluation of correlation using Pearson linear correlation coefficient (PLCC) and Spearman rank order correlation coefficient (SROCC) shows a higher value for the correlation between WBVDM and subjective score. The experimental observations show that WBVDM is able to capture the distortion in blood vessels more effectively and responds weakly to the distortion inherent in the other retinal features.

Finite state representation of hand gesture using key video object plane

The use of hand gestures has become an important part of human computer interaction (HCI) in recent years. Vision-based hand gesture recognition involves visual analysis of hand shape, position and/or movement. Due to co-articulation that occurs during transition from one gesture to the next, problem is encountered in continuous hand gesture recognition. This may be tackled by identifying the key frames in the gesture video sequence. Key frames are the frames that can represent the salient content of a video shot in an abstracted manner. In this paper, we present an object-based scheme for key frame extraction using Hausdorff distance and subsequent local motion analysis by angular circular local motion descriptor (ACLM) for gesture representation. We propose a finite state machine (FSM) in which gestures are represented by the sequence of key frames and the corresponding key frame duration. Experimental results obtained demonstrate the effectiveness of our proposed scheme for key frame extraction and subsequent gesture representation.