Van Huan Nguyen

Reliable detection of eye features and eyes in color facial images using ternary eye-verifier

Eye detection plays an important role in applications related to face recognition. The position of eyes can be used as a reliable reference for other facial feature detection. This paper presents a novel approach for the precise and reliable detection of eyes by introducing a ternary eye-verifier. Initially, the face region is detected by combining color information and the Haar-like feature detector. The face region is then binarized and filtered with circular filters to detect eye candidates at the peaks in the filtered response. Each eye candidate is fed into a ternary eye-verifier that includes a proposed eye feature extractor based on K-means clustering with compensation for variety in iris color. The eye template in the eye-verifier is constructed based on both the knowledge of eye geometry and the detected eye features. The template matching is made by the ternary Hamming distance. Experiments over a collection of FERET face database and house-made face database with different head poses confirm that the proposed method achieves precise and reliable detection of eyes from color facial images with variation in illumination, pose, eye gazing direction, and race.

Inter-level and intra-level deconvolution based image deblurring algorithm for wide field microscopy

This paper proposes an inter-level and intra-level deconvolution based image deblurring algorithm (ILILD) for microscopic images. Pyramid structure is used, and inter-level deconvolution is applied to estimate latent image from coarse level to fine level. The inter-level algorithm is based on total variation regularized Richardson-Lucy scheme, which can estimate latent image with artifacts suppressed. After inter-level deconvolution, intra-level deconvolution is applied. In each pyramid level of image, the residual deconvolution is done as the intra-level deconvolution scheme to recover image edges and details furtherly. Experiments show that ILILD algorithm can estimate latent images in less time and the results have better peak signal to noise ratio, higher image entropies and few artifacts.

Combination of edge and color information for robust preprocessing in facial image quality assessment

With the aim of developing an automatic system to verify if facial images meet ISO/IEC 19794-5 standards and ICAO requirements, this paper proposes a robust image processing method to obtain information for quality evaluation step. Specifically, an adaptive background segmentation and a robust facial feature extraction (including eye centers, four lip features and chin) are proposed. In background segmentation, background information is provided after applying an edge-based segmentation. A color-based segmentation is then used to deal with shadows. In order to overcome the influence of head poses and illumination, which are the main factors of unsuccessful eye detection, an improvement of the circular filter-based eye detection is used to locate eye centers. To accurately detect lip features and chin regardless expressions and presences of beards or mustaches, the proposed method fuses edge and color information together. An experiment was performed on a subset of the FERET and GTAV database, and the experimental results demonstrated the accuracy and robustness of the proposed method.

Blind image deconvolution based on robust stable edge prediction

This paper proposes a robust blind deconvolution method for removing a uniform blur from microscopy images. For the estimation of the kernel - point spread function (PSF) - the stable edge is estimated using a fuzzy edge prediction method. Based on the estimated stable edges, optimizing a blurring objective function leads to a closed form for the estimation of a kernel and latent image. In comparison with existing deconvolution methods based on iterative optimization, the proposed method with a closed-form solution produces a significant decrease in processing time, which is an important barrier in applying deconvolution methods to real-world applications. Experimental results demonstrate the robustness and high efficiency of the proposed method for diverse microscopy images.

Improvement of Accuracy for Human Action Recognition by Histogram of Changing Points and Average Speed Descriptors

Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets. Category: Smart and intelligent computing

An Efficient Pedestrian Detection Approach Using a Novel Split Function of Hough Forests

In pedestrian detection applications, one of the most popular frameworks that has received extensive attention in recent years is widely known as a ‘Hough forest’ (HF). To improve the accuracy of detection, this paper proposes a novel split function to exploit the statistical information of the training set stored in each node during the construction of the forest. The proposed split function makes the trees in the forest more robust to noise and illumination changes. Moreover, the errors of each stage in the training forest are minimized using a global loss function to support trees to track harder training samples. After having the forest trained, the standard HF detector follows up to search for and localize instances in the image. Experimental results showed that the detection performance of the proposed framework was improved significantly with respect to the standard HF and alternating decision forest (ADF) in some public datasets.

Robust feature extraction for facial image quality assessment

With the aim of developing an automatic system to verify if facial images meet ISO/IEC 19794-5 standards and ICAO requirements, this paper proposes a robust method to detect facial features including two eye centers and four lip features. The proposed method restricts the areas where facial features are observed by using the skin color and shape characteristic of faces. Two eye centers are detected independently in the restricted area by means of the circular filters. The use of circular filters makes the algorithm robust to head poses and occlusions, which are the main factors of unsuccessful eye detections. To accurately detect lip features regardless facial expressions and the presence of beard or mustache, the proposed method fuses edge and color information together. An experiment was performed on a subset of the FERET database, and the experimental results demonstrated the accuracy and robustness of the proposed method.

fPADnet: Small and Efficient Convolutional Neural Network for Presentation Attack Detection

The rapid growth of fingerprint authentication-based applications makes presentation attack detection, which is the detection of fake fingerprints, become a crucial problem. There have been numerous attempts to deal with this problem; however, the existing algorithms have a significant trade-off between accuracy and computational complexity. This paper proposes a presentation attack detection method using Convolutional Neural Networks (CNN), named fPADnet (fingerprint Presentation Attack Detection network), which consists of Fire and Gram-K modules. Fire modules of fPADnet are designed following the structure of the SqueezeNet Fire module. Gram-K modules, which are derived from the Gram matrix, are used to extract texture information since texture can provide useful features in distinguishing between real and fake fingerprints. Combining Fire and Gram-K modules results in a compact and efficient network for fake fingerprint detection. Experimental results on three public databases, including LivDet 2011, 2013 and 2015, show that fPADnet can achieve an average detection error rate of 2.61%, which is comparable to the state-of-the-art accuracy, while the network size and processing time are significantly reduced.

Full weighting Hough Forests for object detection

Object detection plays an important role in autonomous video surveillance systems nowadays. Models based on the Hough Forests are widely applied, which use the local patches that vote for the object centers in images. Since these patches vote independently from each other, there is no guarantee that trees built in Hough Forests can obtain optimal parameters for the entire model. This paper proposes a novel method to improve the Hough Forests by introducing weights to each offset in the positive training images to specify the importance of the patch to the training object. Also, all patches in the dataset are weighted and updated during the training process by minimizing the global loss function. The weights are used in both the training and detection phases to obtain a more accurate location of instances in detection images. The proposed method is then evaluated on TUD pedestrian and UIUC car datasets showing promising results compared to recent methods such as Hough Forests, and Alternating Decision Forests.

Automated conformance testing for ISO/IEC 19794-5 Standard on facial photo specifications

This paper proposes effective metrics for quantitative conformance testing for ISO/IEC 19794-5 standard on facial photo specifications. Each metric is normalised to [0, 10], as a quality score of each requirement, to conveniently utilise in facial photo quality validation systems. Furthermore, this paper proposes a robust method of extracting necessary features in the images for automated conformance testing. The proposed extraction method takes advantages of colour, intensity and edge information. Experimental results over a subset of FERET, GTAV, and FIePI databases demonstrated the effectiveness and robustness of the proposed metrics and extraction method.