International Journal of Applied Pattern Recognition (8 papers in press)
A New Interval Type 2 Fuzzy based Pixel Wise Information Extraction for Face Recognition
by Sudesh Yadav, Virendra P. Vishwakarma
Abstract: A new efficient and robust approach based on pixel wise information extraction and fuzzy logic concept is presented here for the application of face recognition (FR). The motivation behind our approach is exploiting the benefit of pixel wise association of individual pixels in discriminating various classes. As all the pixels of an individual face image do not participate equally in identifying a face image from a given set of classes. Therefore, we compute the contribution made by individual pixels in identifying face images using a new interval type 2 fuzzy membership function: an extended concept of fuzzy logics. In this paper, we use a new interval type 2 fuzzy based pixel wise information extraction (NIntTy2FPIE) on input face images for computing the pixel wise association of individual pixels in recognition of a face image in a given dataset. It generates a matrix, containing value in [0, 1], where a value of a pixel in matrix near to one indicates that it is more important in discriminating the classes whereas a value near to zero indicates that it is least important. Thereafter, we apply principle component analysis (PCA) for reducing the computational cost of high dimensional data obtained above. Next, we do classification of unseen data using a variant of nearest neighbor classifier (NNC), called k-NNC. The effectiveness of NIntTy2FPIE based on k- NNC on FR systems is established with different standard datasets. Experiments performed on ORL, Yale and Georgia Tech and AR face database show that our method outperforms with many state-of-art methods and also proves that new interval type 2 membership function (MF) with k-NNC is much more efficient and robust.
Keywords: Face Recognition; Interval Type-2 Fuzzy Logics; π-Membership Function; Classification Approaches.
Artificial Neural Network Based Identification of Bharatanatyam Mudra Images using Eigen Values
by Basavaraj Anami, Venkatesh Bhandage
Abstract: This paper presents a three stage methodology for identification of Mudra images of Bharatanatyam dance. In the first stage, acquired images of Bharatanatyam Mudras are preprocessed to obtain contours of Mudras using canny edge detector. In the second stage, Eigen values are extracted as features. In the third stage, an Artificial Neural Network is used for recognition and classification of unknown Mudras. The work finds application in e-learning of Bharatanatyam dance in particular and dances in general and automation of commentary during concerts.
Keywords: contour of Mudras; Eigen value; Artificial Neural Networks; Bharatanatyam.
Human Action Recognition: A Construction of Codebook by Discriminative Features Selection Approach
by Samra Siddiqui, Muhammad Attique, Khalid Bashir, Muhammad Sharif, Faisal Azam, Muhammad Younus Javed
Abstract: Human Activity Recognition has significance in the domain of pattern recognition. HAR handles the complexity of human physical changes and heterogeneous formats of same human actions performed under dissimilar subjects. Many a novel approaches for HAR emphasize the solution for multidimensional problems. This research contributes a unique technique focusing changing human movement. The purpose is to identify and categorize human actions from video sequences. The interest points are extracted from the subject video and Motion History Images are constructed and analyzed after image segmentation. Discriminative Features are selected and the visual vocabulary is learned from the extracted discriminant features. The extracted discriminant features are then quantized by using visual vocabulary and images are represented based upon frequencies of Visual Words. The visual words are formed from the extracted discriminant features and then a histogram of visual words is developed based upon the feature vectors extracted from motion history images. These feature vectors are used for training Support Vector Machine for the classification of actions into various categories. Benchmarked datasets like KTH and Weizmann are used for evaluation and comparison with existing action recognition approaches depicts the better performance of the adopted strategy.
Keywords: Human activity recognition; foreground extraction; Feature extraction; Feature selection; Classification.
Empirical Investigation of Multiple Query Content Based Image Retrieval
by Mohamed Maher Ben Ismail, Ouiem Bchir
Abstract: Multiple query image retrieval system emerged as a promising solution to effectively understand the user interest, and communicate it to the system in order to retrieve images relevant to the user query. It consists in providing multiple example images to CBIR system in order to better reflect the information meant by the user. In the literature, multiple query based retrieval systems have been proposed. In this paper, we investigate experimentally these existing multiple query content based image retrieval systems and compare them empirically. These approaches are assessed using an image collection from Corel database. We first studied the effect of image query scoring and feature weighting.Then, we compared their performance.
Keywords: Content based image retrieval; multiple query; visual feature; comparative study.
Face recognition performance using Linear Discriminant Analysis and Deep Neural Networks
by Xhevahir Bajrami, Blendi Gashi, Ilir Murturi
Abstract: The face recognition applications deal with large amounts of images and remain difficult to accomplish due to when displayed with images taken in unlimited conditions. Linear Discriminant Analysis (LDA) is a supervised method that uses training samples to obtain the projection matrix for feature extraction, while deep neural networks are trainable for supervised and unsupervised tasks. In this paper, we present our results of experiments done with Linear Discriminant Analysis (LDA) and Deep Neural Networks (DNN) for face recognition, while their efficiency and performance is tested on Labeled Faces in the Wild (LFW) dataset. We used two methods of DNN, k-nearest neighbors algorithm (k-NN) and support vector machine (SVM). Experimental results show that DNN method achieves better recognition accuracy and recognition time is much faster than LDA method in large-scale datasets. Deep learning methods have shown high accuracy even for images coming out of the dataset and with variation in face expressions and lighting.
Keywords: face recognition; lda; dnn.
Human motion analysis based on extraction of skeleton and dynamic time warping algorithm using RGBD camera
by Qing Ye, Chang Qu, Yongmei Zhang
Abstract: Human action analysis is a popular topic in the field of computer vision. It has wide application prospects in intelligent monitoring, virtual reality, pedestrian tracking, etc. This paper present an algorithm for human motion analysis based on extraction of skeleton and dynamic time warping algorithm using RGBD camera .First, to solve the problem of the limitation of information in two-dimensional space, the RGBD camera is adopted to obtain the three-dimensional spatial information of the human body. Then, in the process of feature extraction, 11 skeleton points are selected from the depth image and the relative distance of the space is calculated, reducing the computational complexity significantly. Furthermore, an optimization algorithm of dynamic time warping is introduced so that the adverse effects of time difference are decreased. Finally, the human motion analysis is studied. The experimental results show that the proposed method can recognize single action and double action effectively.
Keywords: RGBD camera; skeleton extraction; feature extraction; dynamic time warping; action recognition.
Authorship Attribution of Short Texts using Multilayer Perceptron
by Nilan Saha, Pratyush Das, Himadri Nath Saha
Abstract: Authorship attribution using stylometry techniques to analyze texts has grown out from earlier times for verifying the authenticity of evidence, authorial identity among other things. With the advent of the digital era, traditional pen- paper writing got replaced by electronic documents making earlier techniques of handwriting analysis impossible because their electronic nature eliminates the informative differences in authorial style. Previously authorship attributions focused mainly on unmasking the author of long pieces of digital texts but in this study, we are going to do the same for short texts that are shared on social platforms and boards. We have used a Multilayer Perceptron to correctly attribute short texts to their authors using a twitter dataset of 4 authors and 400 tweets for each author with 96.44% accuracy
Keywords: Multilayer Perceptron; stylometry.
Database Corpus for Yoruba Handwriting
by Jumoke Ajao
Abstract: Abstract: Non-availability of Yoruba handwritten Database has been a major challenge affecting the validation of the Yoruba handwritten recognition system. This paper presents an ofﬂine Yoruba handwritten Database corpus for validating Yoruba handwritten Word recognition system(YHWR). In this research work, ﬁfty medical pathology words were gotten from medical pathology dictionary. The medical pathology words were translated to their Yoruba equivalence and the translated words were hand written by two hundred(200) indigenous literate writers with appropriate diacritic signs. The offline handwritten data were scanned using 300dpi.The database corpus created; converted the scanned images to different image format, different resolutions and different image sizes, to test the effect of different resolutions, different format and image sizes on Yoruba handwritten recognition system. The digitized images were used to create Yourba handwritten database, which, could be used to validate the handwritten recognition system. The database created is considered a raw data that require some level of preprocessing before it can be used for validating the YHWR system.
Keywords: Yoruba; handwriting; corpus; medical pathology and database.