Authors. in profile

A multi-scale deep quad tree based feature extraction method for the recognition of isolated handwritten characters of popular indic scripts

Sign Language Recognition (SLR) system is a method which allow deaf people to communicate with society. In this study, Real-Time Sign Language recognition system was proposed by using the surface Electromyography (sEMG). To this purpose, sEMG data acquired from subject right forearm for all twenty six American Sign Language gestures. Raw sEMG data was filtered, feature extracted and fed into classification. Support Vector Machine (SVM) with one vs. all approach was used for multi class classification. The experiment result of offline system is reaching a recognition rate of 91.% accuracy and real-time system has a recognition rate of 82.3% accuracy. The results of the proposed system shows that sEMG signal can be used for Real-Time SLR systems.

Real-Time American Sign Language Recognition System Using Surface EMG Signal

https://www.cscjournals.org/download/issuearchive/IJIP/volume6/IJIP_V6_I1.pdf

International journal of image processing (ijip)

Sign Language Recognition (SLR) system is a novel method that allows hard of hearing people to communicate with society. In this study, an American Sign Language (ASL) recognition system was proposed by using the surface Electromyography (sEMG). The objective of this study is to recognize the American Sign Language alphabet letters and allow users to spell words and sentences. For this purpose, sEMG signals are acquired from subject's right forearm for 27 American Sign Language gestures, 26 English alphabet letters, and one for home position. Time domain, frequency domain (band power), power spectral density (band power), and average power features were used as the feature extraction methods. After feature extraction, Principal Component Analysis (PCA) was applied to obtain uncorrelated features. As a classification method, Support Vector Machine and Ensemble Learning algorithm were used and their performances were compared with tabulated results. In conclusion, the results of this study show that sEMG signal can be used for SLR systems.

/pdf/american-sign-language-recognition-system-by-using-surface-1vpyfv3pxk.pdf

American Sign Language Recognition system by using surface EMG signal

The paper presents improved content based image retrieval (CBIR) techniques based on multilevel Block truncation coding using multiple threshold values. Block truncation Coding based features is one of the CBIR methods proposed using color features of image. The approach basically considers red, green and blue planes of image together to compute feature vector. The color averaging methods used here are BTC Level-1, BTC Level-2, BTC Level-3.Here the feature vector size per image is greatly reduced by using mean of each plane and find out the threshold value then divide each plane using threshold value, color averaging is applied to calculate precision and recall to calculate the performance of the algorithm. Instead of using all pixel data of image as feature vector for image retrieval, these six feature vectors can be used, resulting into better performance and if increased the no of feature vector get better performance .The proposed CBIR techniques are tested on generic image database having 1000 images spread across 11 categories. For each proposed CBIR technique 55 queries (5 per category) are fired on the generic image database To compare the performance of image retrieval techniques average precision and recall are computed of all queries. The results have shown the performance improvement (higher precision and recall values) with proposed methods compared to BTC Level-1.

Improved CBIR using Multileveled Block Truncation Coding

Several ways to generalize the Devanagari handwritten character recognition have been proposed in the past. In this paper, novel method of Handwritten Character Recognition with Shape and Texture features has been proposed. The method proposed here does not need the Preprocessing and Character Tokenization. The Shape features and Texture feature are more unique, so a novel technique based on combination of these is derived and proposed here. For extracting shape features standard gradient operator such as Robert, Prewitt, Sobel, Canny and Laplace are used and for texture feature vector quantization technique. The gradient mask images of the character images are obtained and then LBG vector quantization algorithm is applied on these gradient images to get the codebooks of various sizes. These obtained LBG codebooks are considered as shape texture feature vectors for handwritten character recognition. In all 40 variations of the character recognition method are proposed using five gradient operators and 9 code book sizes (from 4 to 1024). For experimentation the database having 72 images from 6 samples per character with 12 different characters is used. The crossover point of precision and recall is considered as performance comparison criteria for proposed character recognition techniques. The best performance is observed in LBG for codebook size 8 of Sobel operator and the next best is seen for codebook sizes 8 and 16 of Prewitt and Laplace gradient mask for feature extraction.

https://ieeexplore.ieee.org/iel7/6521479/6524711/06524768.pdf

Devnagari Handwritten Character Recognition using LBG vector quantization with gradient masks

The paper presents performance comparison of image retrieval methods based on texture feature extraction using Vector Quantization (VQ) codebook generation techniques like LBG and KEVR (Kekre‟s Error Vector Rotation) with assorted color spaces. The image is divided into non overlapping blocks of size 2x2 pixels (each pixel with red, green and blue component). Each block corresponds to one training vector of dimensions 12. The collection of training vectors is called a training set. The texture feature vector of the images are obtained from the most p opular VQ algorithms LBG and KEVR applied on the image training set and codebooks of size 8, 16, 32, 64 128, 256 and 512 are generated. These codebooks are the feature vector set for Content Based Image Retrieval (CBIR). The results are obtained using six different color spaces such as RGB, LUV, YCgCb, YCbCr, YUV and YIQ. For experimentation, the generic image database having 1000 images is used. From the results it is observed that KEVR based CBIR shows better performance over LBG based CBIR. Overall in all codebook sizes KEVR in YUV color space gives the best results with higher precision-recall crossover point values; closely followed by YCbCr color space.

/pdf/assorted-color-spaces-to-improve-the-image-retrieval-using-3a9v1fis2s.pdf

Assorted Color Spaces to improve the Image Retrieval using VQ Codebooks Generated using LBG and KEVR

This paper presents novel texture based content based image retrieval(CBIR) methods using six assorted color spaces i.e RGB, LUV, YCgCb, YIQ, YCbCr, YUV. For extracting texture feature Vector Quantization (VQ) algorithms like Linde Buzo Gray(LBG), Kekre’s Proportionate Error (KPE), Kekre’s Error Vector Rotation (KEVR), Kekre’s Median Codebook Generation (KMCG) and Kekre’s Fast Codebook Generation (KFCG) algorithms are used. The codebook generated from these algorithms act as the feature vector for CBIR system. Seven different codebook sizes varying from 8x12 to 512x12 are generated in six color spaces and using five different VQ algorithms, so in all 210 (7x6x5) techniques are presented here. The proposed image retrieval techniques are tested on generic image database having 1000 images and is independent of the image size and rotation invariant. To test the performance of the proposed CBIR techniques Precision and Recall is used. From the results it is observed that KFCG gives best results with higher precision and recall values. Codebook size 128x12 gives best result in all codebook generation algorithms.

Image retrieval using texture features extracted using lbg, kpe, kfcg, kmcg, kevr with assorted color spaces

Sign language is a widely used and accepted standard for communication by people with hearing and speaking impairments. A sign language is a language which uses visually transmitted sign patterns, instead of acoustically conveyed sound patterns, to deliver the meaning. Several ways to generalize the American sign language recognition have been proposed in the past [14] [15]. In this paper, novel method of American sign language recognition with Shape and Texture features has been proposed. Many of the existing systems require the person gesticulating to use special data acquisition devices like data gloves which are expensive and difficult to handle. We proposes a more flexible vision based approach where the person is free from additional equipment. The Shape features and Texture feature are more unique, so a novel technique based on combination of these is derived and proposed here. For extracting shape features standard gradient operator such as Robert, Prewitt, Sobel, Canny, Freichein, Kirsh and Laplace are used and for texture feature vector quantization techniques are used. The gradient mask images of the character images are obtained and then LBG vector quantization algorithm is applied on these gradient images to get the codebooks of various sizes. These obtained LBG codebooks are considered as shape texture feature vectors for American sign language recognition. The database includes 26 for American sign language alphabets taken by 12 different people. The images are saved in a jpeg file format and stored in separate folder. Thus there are total 312 images were use for our project and 8 code book sizes (from 4 to 512). The nearest neighbour (KNN) algorithm is considered as performance comparison criteria for proposed character recognition techniques. The best performance is observed in LBG for codebook size 8 of Canny operator and the next best is seen for codebook sizes 4 of freichein gradient mask for feature extraction. The LBG VQ [11] design algorithm is an iterative algorithm which requires an initial codebook C. This initial codebook is obtained by the splitting method. In this method, an initial code vector is set as the average of the entire training sequence. This code vector is then split into two. The iterative algorithm is run with these two vectors as the initial codebook. The final two code vectors are splitted into four and the process is repeated until the desired number of code vectors is obtained.

Shrikant P. Sanas

Papers

Improved CBIR using Multileveled Block Truncation Coding

Devnagari Handwritten Character Recognition using LBG vector quantization with gradient masks

Assorted Color Spaces to improve the Image Retrieval using VQ Codebooks Generated using LBG and KEVR

Image retrieval using texture features extracted using lbg, kpe, kfcg, kmcg, kevr with assorted color spaces

Recognition of American sign language using LBG vector quantization