• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권2호
• /
• pp.825-836
• /
• 2016

In this paper, a speed-up technique for the non-local means (NLM) image denoising method based on local binary descriptor (LBD) is proposed. In the NLM, most of the computation time is spent on searching for non-local similar patches in the search window. The local binary descriptor which represents the structure of patch as binary strings is employed to speed up the search process in the NLM. The descriptor allows for a fast and accurate preselection of non-local similar patches by bitwise operations. Using this approach, a tradeoff between time-saving and noise removal can be obtained. Simulations exhibit that despite being principally constructed for speed, the proposed algorithm outperforms in terms of denoising quality as well. Furthermore, a parallel implementation on GPU brings NLM-LBD to real-time image denoising.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4429-4447
• /
• 2018

Local binary descriptors are well-suited for many real-time and/or large-scale computer vision applications, while their low computational complexity is usually accompanied by the limitation of performance. In this paper, we propose a new optimization framework, RLDB (Robust-LDB), to improve a typical region-based binary descriptor LDB (local difference binary) and maintain its computational simplicity. RLDB extends the multi-feature strategy of LDB and applies a more complete region-comparing configuration. A cascade bit selection method is utilized to select the more representative patterns from massive comparison pairs and an online learning strategy further optimizes descriptor for each specific patch separately. They both incorporate LDP (linear discriminant projections) principle to jointly guarantee the robustness and distinctiveness of the features from various scales. Experimental results demonstrate that this integrated learning framework significantly enhances LDB. The improved descriptor achieves a performance comparable to floating-point descriptors on many benchmarks and retains a high computing speed similar to most binary descriptors, which better satisfies the demands of applications.

• ETRI Journal
• /
• 제35권6호
• /
• pp.1021-1028
• /
• 2013

Automatic facial expression recognition is a widely studied problem in computer vision and human-robot interaction. There has been a range of studies for representing facial descriptors for facial expression recognition. Some prominent descriptors were presented in the first facial expression recognition and analysis challenge (FERA2011). In that competition, the Local Gabor Binary Pattern Histogram Sequence descriptor showed the most powerful description capability. In this paper, we introduce hybrid facial representations for facial expression recognition, which have more powerful description capability with lower dimensionality. Our descriptors consist of a block-based descriptor and a pixel-based descriptor. The block-based descriptor represents the micro-orientation and micro-geometric structure information. The pixel-based descriptor represents texture information. We validate our descriptors on two public databases, and the results show that our descriptors perform well with a relatively low dimensionality.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2010년도 춘계학술발표대회
• /
• pp.377-380
• /
• 2010

This paper proposes texture descriptor for texture classification called Local Neighbor Differences (LND). LND is a high discriminating texture descriptor and also robust to illumination changes. The proposed descriptor utilizes the sign of differences between surrounding pixels in a local neighborhood. The differences of those pixels are thresholded to form an 8-bit binary codeword. The decimal values of these 8-bit code words are computed and they are called LND values. A histogram of the resulting LND values is created and used as feature to describe the texture information of an image. Experimental results, with respect to texture classification accuracies using OUTEX_TC_00001 test suite has been performed. The results show that LND outperforms LBP method, with average classification accuracies of 92.3% whereas that of local binary patterns (LBP) is 90.7%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3312-3327
• /
• 2020

Plant diseases are a significant yield and quality constraint for farmers around the world due to their severe impact on agricultural productivity. Such losses can have a substantial impact on the economy which causes a reduction in farmer's income and higher prices for consumers. Further, it may also result in a severe shortage of food ensuing violent hunger and starvation, especially, in less-developed countries where access to disease prevention methods is limited. This research presents an investigation of Directional Local Quinary Patterns (DLQP) as a feature descriptor for plants leaf disease detection and Support Vector Machine (SVM) as a classifier. The DLQP as a feature descriptor is specifically the first time being used for disease detection in horticulture. DLQP provides directional edge information attending the reference pixel with its neighboring pixel value by involving computation of their grey-level difference based on quinary value (-2, -1, 0, 1, 2) in 0°, 45°, 90°, and 135° directions of selected window of plant leaf image. To assess the robustness of DLQP as a texture descriptor we used a research-oriented Plant Village dataset of Tomato plant (3,900 leaf images) comprising of 6 diseased classes, Potato plant (1,526 leaf images) and Apple plant (2,600 leaf images) comprising of 3 diseased classes. The accuracies of 95.6%, 96.2% and 97.8% for the above-mentioned crops, respectively, were achieved which are higher in comparison with classification on the same dataset using other standard feature descriptors like Local Binary Pattern (LBP) and Local Ternary Patterns (LTP). Further, the effectiveness of the proposed method is proven by comparing it with existing algorithms for plant disease phenotyping.

• ETRI Journal
• /
• 제32권5호
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권9호
• /
• pp.4549-4566
• /
• 2017

This work presents a novel facial descriptor, which is named as multiscale adaptive local directional texture pattern (MALDTP) and employed for expression recognition. We apply an adaptive threshold value to encode facial image in different scales, and concatenate a series of histograms based on the MALDTP to generate facial descriptor in term of Gabor filters. In addition, some dedicated experiments were conducted to evaluate the performance of the MALDTP method in a person-independent way. The experimental results demonstrate that our proposed method achieves higher recognition rate than local directional texture pattern (LDTP). Moreover, the MALDTP method has lower computational complexity, fewer storage space and higher classification accuracy than local Gabor binary pattern histogram sequence (LGBPHS) method. In a nutshell, the proposed MALDTP method can not only avoid choosing the threshold by experience but also contain much more structural and contrast information of facial image than LDTP.

• 한국정보통신학회논문지
• /
• 제21권9호
• /
• pp.1674-1680
• /
• 2017

본 논문에서는 고차원 국부이진패턴과 결합베이시안 알고리즘을 이용한 얼굴인증 임베디드 시스템을 제안한다. 또한, 제안된 알고리즘에 대한 임베디드 시스템을 라즈베리파이 3을 이용하여 구현한 결과를 제시한다. 제안된 얼굴인증 알고리즘에 대한 평가는 500명의 얼굴 데이터가 저장된 데이터베이스를 이용하여 수행하였다. 여기서 각각의 얼굴 데이터는 학습용과 테스트용 이미지로 구성하였다. 성능평가를 위한 척도로는 주성분분석법의 차원에 따른 스코어 분포와 얼굴인증 시간을 이용하였다. 그 결과, 최적화된 임베디드 환경에서 우수한 얼굴인증 성능을 가지는 임베디드 시스템을 상대적으로 저렴한 비용으로 구현할 수 있음을 확인하였다.

• 전자공학회논문지CI
• /
• 제47권4호
• /
• pp.34-43
• /
• 2010

질감 정보는 객체 인식과 분류에서 중요한 역할을 하고 있다. 정확한 질환 판별을 위해 분류에서 사용되는 질감 특징은 식별성이 높아야 한다. 본 논문에서는 질감-기반 영상 검색 및 폐기종 진단을 위해 컴퓨터 조력진단(Computer-Aided Diagnosis) 시스템을 위한 새로운 질감 기술자를 제안한다. 제안한 질감 기술자는 이웃화소간의 차이값과 중심화소와 이웃화소간의 차이 값의 결합에 기반을 두고 있어 결합된 주변화소 차이(Combined Neighborhood Difference; CND)라고 한다. 화소들간의 CND는 비교후 이진 코드워드로 변환된다. 그다음에, 식별성이 높은 값을 생성하기 위하여 이진 계수가 코드워드에 할당된다. 이와 같은 값들의 분포가 계산되어 질감 특징 벡터를 구성한다. Outex와 Brodatz 데이터집합을 이용한 질감 특징 분류에 관련하여 CND는 92.5%의 정확성을 보이는 데 비해, LBP, LND와 Gabor 픽터는 89.3%, 90.7%와 83.6%의 정확성을 각각 보여준다. 본 논문에서는 CND를 이용한 폐기종의 진단 기능을 CAD 시스템에서 구현하였다.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.