Face recognition with enhanced local directional patterns

Zhong, Fujin; Zhang, Jiashu

doi:10.1016/j.neucom.2013.03.020

Cited by 84 publications

(34 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biometrics is concerned with these characteristics. Biometrics has received a great deal of attention in recent years, due to its high discriminatory performance in many areas such as surveillance, identification, and human-computer interaction (Zhong & Zhang, 2013) (Guan et al, 2010) (Jain et al, 2000). These characteristics are generally classified under two headings as physiological and behavioral (Jain & Ross, 2008).…”

Section: Structured Abstractmentioning

confidence: 99%

Altigen Sayisal Görüntü İşlemede Gri̇-Sevi̇ye Eş-Oluşum Matri̇sleri̇ İle Yüz Tanima

Cevik¹

2019

TurkishStudies

View full text Add to dashboard Cite

Face Recognition has been an attractive field of research for decades, because face is one of the most useful and deterministic biometrics. Image processing is called square pixel-based image processing since its existence. However, hexagonal image processing, which is based on the idea of designing and processing pixels as hexagons, has been shown to provide significant benefits in terms of time and memory savings. Almost all of the face recognition methods proposed and implemented so far are based on square pixel based image processing. Based on the limited number of studies on face recognition in hexagonal pixel based image processing, a hexagonal image processing based face recognition method is proposed in this study. The method proposed in this study is inspired by Grey Level Co-occurrence Matrices (GLCM), which is one of the most fundamental of square pixel based face recognition methods. The method is named Hex_Direct_GLCM because it is based on the square pixel-based basic GLCM method. Since hardwarebased hexagonal pixel-based image processing is not yet available, hexagonal pixel-based equivalents of square pixel-based digital images are artificially created by software. The hexagonal pixel base equivalents of the steps followed in the GLCM method are performed, and then face recognition accuracy performance analysis is performed on different data sets. As presented in the simulation results, the Hex_Direct_GLCM method provides competitive results with high accuracy in terms of face recognition as well as the success in saving resources such as time and space.

show abstract

Section: Structured Abstractmentioning

confidence: 99%

Altigen Sayisal Görüntü İşlemede Gri̇-Sevi̇ye Eş-Oluşum Matri̇sleri̇ İle Yüz Tanima

Cevik¹

2019

TurkishStudies

View full text Add to dashboard Cite

show abstract

“…Another approach known as Extended Local Binary Pattern [12] is more effective than LBP. Some advanced approaches based on LBP such as Local Directional Pattern [14], Enhanced Local Directional Pattern [39], eight Local Directional Pattern [9] have also been tried by various research groups. These methods perform convolution of the image with different types of filters, better known as Kirsch compass masks.…”

Section: Related Workmentioning

confidence: 99%

Recognizing gender from human facial regions using genetic algorithm

et al. 2018

View full text Add to dashboard Cite

Recently, recognition of gender from facial images has gained a lot of importance. There exist a handful of research work that focus on feature extraction to obtain gender specific information from facial images. However, analyzing different facial regions and their fusion help in deciding the gender of a person from facial images. In this paper, we propose a new approach to identify gender from frontal facial images that is robust to background, illumination, intensity, and facial expression. In our framework, first the frontal face image is divided into a number of distinct regions based on facial landmark points that are obtained by the Chehra model proposed by Asthana et al. The model provides 49 facial landmark points covering different regions of the face, e.g. forehead, left eye, right eye, lips. Next, a face image is segmented into facial regions using landmark points and features are extracted from each region. The Compass LBP feature, a variant of LBP feature, has been used in our framework to obtain discriminative gender specific information. Following this, a Support Vector Machine based classifier has been used to compute the probability scores from each facial region. Finally, the classification scores obtained from individual regions are combined with a genetic algorithm based learning to improve 2 Avirup Bhattacharyya et al.the overall classification accuracy. The experiments have been performed on popular face image datasets such as Adience, cFERET (color FERET), LFW and two sketch datasets, namely CUFS and CUFSF. Through experiments, we have observed that, the proposed method outperforms existing approaches.The face of a human being reveals useful information about his/her identity, ethnicity, age, gender, expression, and emotion. Gender identification from facial images plays an important role in various computer vision based applications. It is possible for human beings to correctly determine gender by looking at the facial appearance. The advancements of computer vision technologies have inspired the researchers to design systems capable of performing similar functions [15,26,30]. Human computer interaction system, surveillance system, content based indexing and searching, biometric, and targeted advertising are some of the areas where it has been widely used. In a typical face recognition system, researchers face a number of challenges due to variations in pose, illumination, occlusion, expression, and lower resolution that essentially hamper a system's performance. Hence, the challenge is to design a system that is fairly invariant to changes in illumination, pose, resolution, and facial expression. These challenges have been effectively dealt with by the authors in [20,27,36]. However, gender recognition in such varying conditions has not been fully addressed yet. This paper deals with gender recognition of frontal face images with variations in illumination, pose, facial expression and image resolution.Feature dimension and computational complexity are important aspects that a typical gen...

show abstract

“…Different from LBP-based methods, Ren et al [28] considered that Gabor features in each band can be combined by a vector, and proposed a band-reweighed Gabor kernel embedding algorithm to deal with face recognition with illumination or pose variation. Other feature extraction-based methods such as Local Directional Patterns (LDP) [29], Enhanced LDP [30], Local Directional Number Patterns (LDN) [31], AHELDP [32], WFSDMS [33] also have gained much attention because of their robustness to several kinds of variations, but they still have some room to improve the performance when illumination variation dominates the main variation.…”

Section: Introductionmentioning

confidence: 99%

Discriminative multi-layer illumination-robust feature extraction for face recognition

Dai

Ren

et al. 2017

Pattern Recognition

View full text Add to dashboard Cite

Tackling illumination variation is a major problem and it is also an important challenge for practical face recognition systems. Some related methods consider that lighting intensity components mainly lie in large-scale features, and they use a lot of image decomposition techniques to extract the small-scale illuminationinvariant features and remove the large-scale features from original face images. However, it argues that the large-scale features contain a lot useful information which can be further extracted, and the small-scale illumination-invariant features are not robust enough due to they contain some detrimental features (noise, etc.).

show abstract

Face recognition with enhanced local directional patterns

Cited by 84 publications

References 29 publications

Altigen Sayisal Görüntü İşlemede Gri̇-Sevi̇ye Eş-Oluşum Matri̇sleri̇ İle Yüz Tanima

Altigen Sayisal Görüntü İşlemede Gri̇-Sevi̇ye Eş-Oluşum Matri̇sleri̇ İle Yüz Tanima

Recognizing gender from human facial regions using genetic algorithm

Discriminative multi-layer illumination-robust feature extraction for face recognition

Contact Info

Product

Resources

About