Geometric Feature Based Face-Sketch Recognition

This paper presents a novel facial sketch image or face-sketch recognition approach based on facial feature extraction. To recognize a face-sketch, we have concentrated on a set of geometric face features like eyes, nose, eyebrows, lips, etc and their length and width ratio because it is difficult to match photos and sketches because they belong to two different modalities. In this system, first the facial features/components from training images are extracted, then ratios of length, width, and area etc. are calculated and those are stored as feature vectors for individual images. After that the mean feature vectors are computed and subtracted from each feature vector for centering of the feature vectors. In the next phase, feature vector for the incoming probe face-sketch is also computed in similar fashion. Here, K-NN classifier is used to recognize probe face-sketch. It is experimentally verified that the proposed method is robust against faces are in a frontal pose, with normal lighting and neutral expression and have no occlusions. The experiment has been conducted with 80 male and female face images from different face databases. It has useful applications for both law enforcement and digital entertainment.

Multi-Sensor Image Fusion Based on Moment Calculation

An image fusion method based on salient features is proposed in this paper. In this work, we have concentrated on salient features of the image for fusion in order to preserve all relevant information contained in the input images and tried to enhance the contrast in fused image and also suppressed noise to a maximum extent. In our system, first we have applied a mask on two input images in order to conserve the high frequency information along with some low frequency information and stifle noise to a maximum extent. Thereafter, for identification of salience features from sources images, a local moment is computed in the neighborhood of a coefficient. Finally, a decision map is generated based on local moment in order to get the fused image. To verify our proposed algorithm, we have tested it on 120 sensor image pairs collected from Manchester University UK database. The experimental results show that the proposed method can provide superior fused image in terms of several quantitative fusion evaluation index.

An Approach: Modality Reduction and Face-Sketch Recognition

To recognize face sketch through face photo database is a challenging task for todays researchers. Because face photo images in training set and face sketch images in testing set have different modality. Difference between two face photos of difference person is smaller than the difference between same person in a face photo and face sketched. In this paper, for reduction of the modality between face photo and face sketch we first bring face photo and face sketch images in a new dimension using 2D Discrete Haar wavelet transform with scale 3 followed by a negative approach. After that, extract features from transformed images using Principal Component Analysis (PCA). Thereafter, we use SVM classifier and K-NN classifier for better classification. Our proposed method is experimentally verified by its robustness against faces that are captured in a good lighting condition and in a frontal pose. The experiment has been conducted with 100 male and female face images as training set and 100 male and female face sketch images as testing set collected from CUHK training and testing cropped photos and CUHK training and testing cropped sketches.