Sajid Ali Khan

Gender classification using image processing techniques: A survey

Classification has emerged as a leading technique for problem solution and optimization. Classification has been used extensively in several problems domains. Automated gender classification is an area of great significance and has great potential for future research. It offers several industrial applications in near future such as monitoring, surveillance, commercial profiling and human computer interaction. Different methods have been proposed for gender classification like gait, iris and hand shape. However, majority of techniques for gender classification are based on facial information. In this paper, a comparative study of gender classification using different techniques is presented. The major emphasis of this work is on the critical evaluation of different techniques used for gender classification. The comparative evaluation has highlighted major strengths and limitations of existing gender classification techniques. Taking an overview of these major problems, our research is focused on summarizing the literature by highlighting its strengths and limitations. This study also presents several areas of future research in the domain of gender classification.

Reliable facial expression recognition for multi-scale images using weber local binary image based cosine transform features

Accurate recognition of facial expression is a challenging problem especially from multi-scale and multi orientation face images. In this article, we propose a novel technique called Weber Local Binary Image Cosine Transform (WLBI-CT). WLBI-CT extracts and integrates the frequency components of images obtained through Weber local descriptor and local binary descriptor. These frequency components help in accurate classification of various facial expressions in the challenging domain of multi-scale and multi-orientation facial images. Identification of significant feature set plays a vital role in the success of any facial expression recognition system. Effect of multiple feature sets with varying block sizes has been investigated using different multi-scale images taken from well-known JAFEE, MMI and CK+ datasets. Extensive experimentation has been performed to demonstrate that the proposed technique outperforms the contemporary techniques in terms of recognition rate and computational time.

Efficient gender classification methodology using DWT and PCA

Recognition of gender from face images has accomplished great popularity and also enlightened some new research problems. In this paper, we presented a new technique for gender classification using DWT and PCA. The technique has shown performance better than existing gender classification techniques. Experiments were carried out on standard face database used in various existing works of literature. Our proposed method provides high accuracy and is resilient to brightness changes comparison to those techniques which are in practice.

Facial expression recognition using computationally intelligent techniques

Facial expressions classification is a fast growing research area. Lots of contribution has been made in this area by researchers from fields of computer science, computer vision, artificial intelligence and psychology. There are many applications that use facial expression classification to identify the behavior, emotion, feelings and opinion of a person. Facial expression classification is not a trivial task as there are many factors that need to be accounted like low quality of images, noise, and shape/color of image. In this article, we have proposed an efficient facial expression classification scheme. In the first step, we perform some pre-processing steps like face detection and histogram equalization inorder to reduce the data dimenions and normalize the illumination effects. Then, an efficient feature extraction technique is used to extract the relevant face features. In the last step, we train and test Support Vector Machine (SVM) classifier to classify the facial expressions. Emirical results obtained using the JAFFE database suggest that the proposed technique produces impressive results by utilzing the best facial features.

Kruskal-Wallis-Based Computationally Efficient Feature Selection for Face Recognition

Face recognition in todays technological world, and face recognition applications attain much more importance. Most of the existing work used frontal face images to classify face image. However these techniques fail when applied on real world face images. The proposed technique effectively extracts the prominent facial features. Most of the features are redundant and do not contribute to representing face. In order to eliminate those redundant features, computationally efficient algorithm is used to select the more discriminative face features. Extracted features are then passed to classification step. In the classification step, different classifiers are ensemble to enhance the recognition accuracy rate as single classifier is unable to achieve the high accuracy. Experiments are performed on standard face database images and results are compared with existing techniques.

Efficient Gender Classification Using Interlaced Derivative Pattern and Principal Component Analysis

With the wealth of image data that is now becoming increasingly accessible through the advent of the world wide web and proliferation of cheap, high quality digital cameras it is becoming ever more desirable to be able to automatically classify Gender into appropriate category such that intelligent agents and other such intelligent software might make better informed decisions regarding them without a need for excessive human intervention. In this paper, we present a new technique which provides superior performance superior than existing gender classification techniques. We first detect the face portion using Voila Jones face detector and then Interlaced Derivative Pattern (IDP)extract discriminative facial features for gender which are passed through Principal Component Analysis (PCA) to eliminate redundant features and thus reduce dimension. Keeping in mind strengths of different classifiers three classifiers K-nearest neighbor, Support Vector Machine and Fisher Discriminant Analysis are combined, which minimizes the classification error rate. We have used Stanford University Medical students (SUMS) face database for our experiment. Comparing our results and performance with existing techniques our proposed method provides high accuracy rate and robustness to illumination change.

Robust face recognition using computationally efficient features

Face recognition has received enormous fame in the field of pattern recognition and computer vision. Being a demanding area intensive research has been done by many researchers for more than a decade. However no standard technique exists for extracting the significant features of facial images in different categories. Techniques found in literature produces high accuracy but are computationally expensive which are not applicable in real time applications. In this paper, two well known methods, Discrete Wavelet Transform (DWT) and Weber Local Descriptor (WLD) are used to extract the face discriminative features. First for both types of features, the recognition accuracy is separately measured. In the next step, both types of features are fused using the concatenation method to improve the accuracy rate. To select more discriminative features and reduce data dimensions, computationally efficient algorithm (Kruskal-Wallis) is used. In the last step, three classifiers (SVM, KNN and BPNN) ensemble to improve the accuracy rate. Proposed technique is more efficient in terms of time complexity as compared to GA and PSO. Yale face database is used for all experiments. The proposed technique is highly robust to facial variations like occlusion, illumination and expression change and computationally efficient as compared to existing methods.

Crop classification using feature extraction from satellite imagery

Plants are a major source of food stuff, medicine and industry. However it is an important and difficult task to recognize species of crop on earth. Therefore it is pertinent to design an appropriate recognition system of crops. As the frontier of space technology is progressed rapidly, remote sensing provides very convenient resource for development in agriculture. In this paper, we proposed a new method for crop classification from satellite imagery. In this method, first of all, we assembled satellite imagery database of different crops and then extract Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) features from each crop and then classify them by different individual classifiers. At the end we described analysis of different classifiers that which classifier performed best. Various techniques have been compared against our proposed model for determining the supremacy of our model and results have shown significant improvement in accuracy and reliability.

Biometric template security: an overview

Purpose The security of the stored biometric template is itself a challenge. Feature transformation techniques and biometric cryptosystems are used to address the concerns and improve the general acceptance of biometrics. The purpose of this paper is to provide an overview of different techniques and processes for securing the biometric templates. Furthermore, the paper explores current research trends in this area. Design/methodology/approach In this paper, the authors provide an overview and survey of different features transformation techniques and biometric cryptosystems. Findings Feature transformation techniques and biometric cryptosystems provide reliable biometric security at a high level. There are many techniques that provide provable security with practical viable recognition rates. However, there remain several issues and challenges that are being faced during the deployment of these technologies. Originality/value This paper provides an overview of currently used techniques for securing biometric templates and also outlines the related issues and challenges.

Gender Classification Using Local Binary Pattern and Particle Swarm Optimization

Gender classification is the phenomena in which a face image is analyzed and recognized by a computer. Feature extraction is the key step of gender classification. In this paper, we present a method which efficiently classifies gender by extracting the key optimized features. We have used Local Binary Pattern (LBP) to extract facial features. As LBP features contain many redundant features, Particle Swarm Optimization (PSO) was applied to get optimized features. We performed different numbers of experiments on FERET face database and report 95.5 % accuracy.