Filter Design and Performance Evaluation for Fingerprint Image Segmentation

XFinger-Net: Pixel-Wise Segmentation Method for Partially Defective Fingerprint Based on Attention Gates and U-Net

Partially defective fingerprint image (PDFI) with poor performance poses challenges to the automated fingerprint identification system (AFIS). To improve the quality and the performance rate of PDFI, it is essential to use accurate segmentation. Currently, most fingerprint image segmentations use methods with ridge orientation, ridge frequency, coherence, variance, local gradient, etc. This paper proposes a method of XFinger-Net for segmenting PDFIs. Based on U-Net, XFinger-Net inherits its characteristics. The attention gate with fewer parameters is used to replace the cascaded network, which can suppress uncorrelated regions of PDFIs. Moreover, the XFinger-Net implements a pixel-level segmentation and takes non-blocking fingerprint images as an input to preserve the global characteristics of PDFIs. The XFinger-Net can achieve a very good segmentation effect as demonstrated in the self-made fingerprint segmentation test.

A Kinect-Based Segmentation of Touching-Pigs for Real-Time Monitoring

Segmenting touching-pigs in real-time is an important issue for surveillance cameras intended for the 24-h tracking of individual pigs. However, methods to do so have not yet been reported. We particularly focus on the segmentation of touching-pigs in a crowded pig room with low-contrast images obtained using a Kinect depth sensor. We reduce the execution time by combining object detection techniques based on a convolutional neural network (CNN) with image processing techniques instead of applying time-consuming operations, such as optimization-based segmentation. We first apply the fastest CNN-based object detection technique (i.e., You Only Look Once, YOLO) to solve the separation problem for touching-pigs. If the quality of the YOLO output is not satisfied, then we try to find the possible boundary line between the touching-pigs by analyzing the shape. Our experimental results show that this method is effective to separate touching-pigs in terms of both accuracy (i.e., 91.96%) and execution time (i.e., real-time execution), even with low-contrast images obtained using a Kinect depth sensor.

Convolution Comparison Pattern: An Efficient Local Image Descriptor for Fingerprint Liveness Detection

We present a new type of local image descriptor which yields binary patterns from small image patches. For the application to fingerprint liveness detection, we achieve rotation invariant image patches by taking the fingerprint segmentation and orientation field into account. We compute the discrete cosine transform (DCT) for these rotation invariant patches and attain binary patterns by comparing pairs of two DCT coefficients. These patterns are summarized into one or more histograms per image. Each histogram comprises the relative frequencies of pattern occurrences. Multiple histograms are concatenated and the resulting feature vector is used for image classification. We name this novel type of descriptor convolution comparison pattern (CCP). Experimental results show the usefulness of the proposed CCP descriptor for fingerprint liveness detection. CCP outperforms other local image descriptors such as LBP, LPQ and WLD on the LivDet 2013 benchmark. The CCP descriptor is a general type of local image descriptor which we expect to prove useful in areas beyond fingerprint liveness detection such as biological and medical image processing, texture recognition, face recognition and iris recognition, liveness detection for face and iris images, and machine vision for surface inspection and material classification.