Narrow Results

Due to noisy acquisition devices and variation in impression conditions, the ridgelines of fingerprint images are mostly corrupted by various kinds of noise causing cracks, scratches and bridges in the ridges as well as blurs. These cause matching errors in fingerprint recognition. For an effective recognition the correct ridge pattern is essential which requires the enhancement of fingerprint images. Segment by segment analysis of the fingerprint pattern yields various ridge direction and frequencies. By selecting a directional filter with correct filter parameters to match ridge features at each point, we can effectively enhance fingerprint ridges. This paper proposes a fingerprint image enhancement based on CNN Gabor-Type filters.

Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.

Scene analysis is so far one of the most important topics in machine vision. In this paper, we present an integrated scene analysis model, namely SCENOGRAM (Scene analysis using CompositENeural Oscillatory-based elastic GRAph Model). Basically the proposed scene analyzer is based on the integration of the composite neural oscillatory model with our elastic graph dynamic link model. The system involves: (1) multifrequency bands feature extraction scheme using Gabor filters, (2) automatic figure-ground object segmentation using a composite neural oscillatory model, and (3) object matching using an elastic graph dynamic link model.

From the implementation point of view, we introduce an intelligent agent based scene analysis and object identification solution using the SCENOGRAM technology. From the experimental point of view, a scene gallery of over 6000 color scene images is used for automatic scene segmentation testing and object identification test. An overall correct invariant facial recognition rate of over 87% is attained. It is anticipated that the implementation of the SCENOGRAM can provide an invariant and higher-order intelligent object (pattern) encoding, searching and identification solution for future intelligent e-Business.

This paper presents a multimodal approach for a biometrics verification system. It is based on face and hand images captured by a cell phone. The algorithm includes all parts that are required for face and hand verification, such as feature extraction, classification and authentication. To find local facial features, such as eyes, mouth and nose, we apply a point distribution model and active shape models. We use the same system to find distinctive points in hand geometry. The face feature vector is constructed by applying a Gabor filter to the image and extracting the key points found by an active shape model. The palm feature vector contains characteristics of the hand geometry features. A support vector machine (SVM) is applied to verify the identity of the user. One SVM machine is built for each person in the database to distinguish that person from others. To test the algorithm we built our own database containing face and hand images taken by a cell phone camera. The database contains 480 frontal face images and 120 hand images of 30 persons (16 face images and 4 hand images per person).

Driver fatigue is a significant factor in many traffic accidents. We propose a novel approach for driver fatigue detection from facial image sequences, which is based on multiscale dynamic features. First, Gabor filters are used to get a multiscale representation for image sequences. Then Local Binary Patterns are extracted from each multiscale image. To account for the temporal aspect of human fatigue, the LBP image sequence is divided into dynamic units, and a histogram of each dynamic unit is computed and concatenated as dynamic features. Finally a statistical learning algorithm is applied to extract the most discriminative features from the multiscale dynamic features and construct a strong classifier for fatigue detection. The proposed approach is validated under real-life fatigue conditions. The test data includes 600 image sequences with illumination and pose variations from 30 people's videos. Experimental results show the validity of the proposed approach, and a correct rate of 98.33% is achieved which is much better than the baselines.

The two-dimensional (2D) Gabor function has been recognized as a very useful tool in feature extraction of image, due to its optimal localization properties in both spatial and frequency domain. This paper presents a novel palmprint feature extraction method based on the statistics of decomposition coefficients of the Gabor wavelet transform. It is experimentally found that the magnitude coefficients of the Gabor wavelet transform within each subband uniformly to approximate the Lognormal distribution. Based on this fact, we create the palmprint representation using two simple statistics (mean and standard deviation) as feature components after applying the logarithmic transformation of Gabor filtered magnitude coefficients for each subband with different orientations and scales. The optimum setting of the number of Gabor filters and orientation of each Gabor filter is experimentally determined. For palmprint recognition, the popularly used Fisher Linear Discriminant (FLD) analysis is further applied on the constructed feature vectors to extract discriminative features and reduce dimensionality. All experiments are both executed over the CCD-based HongKong PolyU Palmprint Database of 7752 images and the scanner-based BJTU_PalmprintDB (V1.0) of 3460 images. The results demonstrate the effectiveness of the proposed palmprint representation in achieving the improved recognition performance.

Biometrics-based authentication is an effective approach which is used for automatically recognizing a person's identity. Recently, it has been found that the finger-knuckle-print (FKP), which refers to the texture pattern produced by the finger knuckle bending, is highly unique and can be used as a biometric identifier. In this paper, we present an effective FKP recognition scheme for personal identification and identity verification. This method is a new encoding scheme based on local binary pattern (LBP). Each image first is decomposed in several blocks, each block is convolved with a bank of Gabor filters and then, the LBPs histograms are extracted from the convolved images. Finally, a BioHashing approach is applied on the obtained fixed-length feature vectors. Extensive experiments conducted over the Poly-U FKP database demonstrated the efficiency and effectiveness of our proposed method.

Gabor filters are parametric functions that are located in both the spatial and frequency domains, they are used in digital signal processing and have been combined with the fractal dimension in the biometric recognition of the iris of the eye and oil exploration to identify the layers that form a soil structure. In this work, we present an example of a Gabor filter that does not preserve fractal dimension, which affects the efficiency of the methods of recognition. In this sense, S. Albeverio, M. Pratsiovytyi, and G. Torbin provide a study on the functions that preserve the fractal dimension and show that those that have a decomposable domain such that they have the property of being bi-Lipschitz on each element of the decomposition, then they will preserve the dimension, however, in this investigation, it is proven that the Gabor filter is not a function of this kind. Therefore, as a main result, the conditions on the parameters are provided for the Gabor filters to preserve it.

Increasing amount of paper documents are produced and received by many organizations. Frequently, they have to be digitized for electronic archiving and later information retrieval or data mining, requiring scanning and OCR. Since OCR techniques are language dependent, the language of the original document must be identified first by advanced technology. This paper describes two methods of identifying Oriental languages among four language groups, i.e. Oriental, Roman, Cyrillic, and Arabic. One method is based on features extracted from the shapes of words and letters, while the other is based on global analysis of text pieces using Gabor filters. Experimental results on hundreds of both clean and noisy documents indicate that the proposed classification approaches look quite promising. The use of linguistic analysis to enhance the results is also discussed.

Iris recognition has been recently given greater attention in human identification and it is becoming increasingly an active topic in research. This paper presents a novel iris recognition method based on multi-channel Gabor filtering and uniform local binary patterns (ULBP). First, the eye image is processed in order to obtain a segmented and normalized eye image by applying Hough transform and polar transformation. Second, the iris image is analyzed by Gabor filters to extract the global features of texture details. Then, ULBP operators are applied in each transformed image to describe the local arrangement of iris texture patterns. Next, the obtained representation is partitioned in blocks. Finally, we have encoded the local relationships between statistical measures computed in blocks to form a template of 240 bytes. We estimate the similarity between irises by computing the modified Hamming distance between templates. Tests were carried out on CASIA v3 iris database. Experimental results illustrate the effectiveness and robustness of ULBP to extract rich local and global information of iris texture when combined with simultaneously multi-blocks and multi-channel method. The comparative evaluations illustrate the good discriminative properties of extracted features for iris recognition.

Hyperspectral imaging (HSI) has shown great potential in the use of paddy variety identification. However, the quality of HSI images taken by a hyperspectral camera under non-ideal illumination is vulnerable to environmental influences such as shadows and noises, leading to a degraded identification result. This problem is addressed in this study by a two-stage image processing method. First, to eliminate the influence of shadows, a grayscale image based on the reflectance slope is synthesized. The synthetic reflectance slope image (SRSI) is binarized for image segmentation and shape features extraction. Secondly, an HSI image de-noising technology based on weighted spatial filtering (WSF), which integrates both spatial and spectral information of the HSI image, is proposed to reduce the influence of noises. Finally, the extracted shape, spectral and texture features are combined and input into the support vector machine for paddy variety identification. Four varieties of paddy with different origins were tested in the experiments. The experiment results showed that compared with color images, the SRSIs could help obtain more accurate shape features. The results also showed that the WSF method can significantly reduce noises and improves the paddy variety identification accuracy.

This chapter reviews and discusses various aspects of texture analysis. The concentration is on the various methods of extracting textural features from images. The geometric, random field, fractal, and signal processing models of texture are presented. The major classes of texture processing problems such as segmentation, classification, and shape from texture are discussed. The possible application areas of texture such as automated inspection, document processing, and remote sensing are summarized. A bibliography is provided at the end for further reading.

This chapter reviews and discusses various aspects of texture analysis. The concentration is on the various methods of extracting textural features from images. The geometric, random field, fractal, and signal processing models of texture are presented. The major classes of texture processing problems such as segmentation, classification, and shape from texture are discussed. The possible application areas of texture such as automated inspection, document processing, and remote sensing are summarized. A bibliography is provided at the end for further reading.