• 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.

• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1264-1274
• /
• 2015

Human action recognition received many interest in the computer vision community. Most of the existing methods focus on either construct robust descriptor from the temporal domain, or computational method to exploit the discriminative power of the descriptor. In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action. We propose an novel framework where introduces local action attributes to represent an action for the final human action categorization. The local action attributes are defined for each body part which are independent from the global action. The resulting attribute descriptor is used to jointly model human action to achieve robust performance. In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes. Experiments on the KTH dataset and the MV-TJU dataset show that our local action attribute based descriptor improve action recognition performance.

• ETRI Journal
• /
• 제24권1호
• /
• pp.23-30
• /
• 2002

MPEG-7 Visual Standard specifies a set of descriptors that can be used to measure similarity in images or video. Among them, the Edge Histogram Descriptor describes edge distribution with a histogram based on local edge distribution in an image. Since the Edge Histogram Descriptor recommended for the MPEG-7 standard represents only local edge distribution in the image, the matching performance for image retrieval may not be satisfactory. This paper proposes the use of global and semi-local edge histograms generated directly from the local histogram bins to increase the matching performance. Then, the global, semi-global, and local histograms of images are combined to measure the image similarity and are compared with the MPEG-7 descriptor of the local-only histogram. Since we exploit the absolute location of the edge in the image as well as its global composition, the proposed matching method can retrieve semantically similar images. Experiments on MPEG-7 test images show that the proposed method yields better retrieval performance by an amount of 0.04 in ANMRR, which shows a significant difference in visual inspection.

• ETRI Journal
• /
• 제40권4호
• /
• pp.499-510
• /
• 2018

A vector space based augmented structural kinematic (VSASK) feature descriptor is proposed for human activity recognition. An action descriptor is built by integrating the structural and kinematic properties of the actor using vector space based augmented matrix representation. Using the local or global information separately may not provide sufficient action characteristics. The proposed action descriptor combines both the local (pose) and global (position and velocity) features using augmented matrix schema and thereby increases the robustness of the descriptor. A multiclass support vector machine (SVM) is used to learn each action descriptor for the corresponding activity classification and understanding. The performance of the proposed descriptor is experimentally analyzed using the Weizmann and KTH datasets. The average recognition rate for the Weizmann and KTH datasets is 100% and 99.89%, respectively. The computational time for the proposed descriptor learning is 0.003 seconds, which is an improvement of approximately 1.4% over the existing methods.

• 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)
• /
• 제4권3호
• /
• pp.305-323
• /
• 2010

This paper proposes an efficient and yet powerful local descriptor called phase-space partition based descriptor (PPD). This descriptor is designed for the mobile image matching and retrieval. PPD, which is inspired from SIFT, also encodes the salient aspects of the image gradient in the neighborhood around an interest point. However, without employing SIFT's smoothed gradient orientation histogram, we apply the region based gradient statistics in phase space to the construction of a feature representation, which allows to reduce much computation requirements. The feature matching experiments demonstrate that PPD achieves favorable performance close to that of SIFT and faster building and matching. We also present results showing that the use of PPD descriptors in a mobile image retrieval application results in a comparable performance to SIFT.

• 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.

• 반도체디스플레이기술학회지
• /
• 제12권4호
• /
• pp.33-38
• /
• 2013

Image retrieval is one of the most exciting and fastest growing research fields in the area of multimedia technology. As the amount of digital contents continues to grow users are experiencing increasing difficulty in finding specific images in their image libraries. This paper proposes an efficient image descriptor which uses a local color and texture in the non-overlapped block images. To evaluate the performance of the proposed method, we assessed the retrieval efficiency in terms of ANMRR with common image dataset. The experimental trials revealed that the proposed algorithm exhibited a significant improvement in ANMRR, compared to Dominant Color Descriptor and Edge Histogram Descriptor.

• 대한전자공학회논문지SP
• /
• 제44권1호
• /
• pp.10-16
• /
• 2007

본 논문에서는 색상의 공간적인 상관관계와 질감 모멘트를 이용한 내용기반 영상 검색 기법을 제안한다. 이를 위해, 색상의 공간적인 상관관계를 표현하는 새로운 색상 기술자를 제안하고, 또한 제안된 색상 기술자와 국부적인 푸리에 변환에 기반한 질감 특성을 결합한 영상 검색 방법을 제안한다. 일반적으로 색상의 공간적인 상관관계를 표현하기 위해서 컬러 코렐로그램(color correlogram)이 사용되고 있다. 하지만 컬러 코렐로그램은 중심화소에 따른 이웃한 화소들의 색상 분포를 확률적으로 잘 나타내는 장점이 있지만, 색상의 구조적인 정보를 표현하지 못하는 단점이 있다. 그러므로 본 논문에서는 색상의 분포와 구조적인 정보를 표시할 수 있는 새로운 색상 기술자를 제안한다. 제안하는 새로운 색상 기술자는 중심 화소와 이웃 화소들과의 색상 거리를 계산한 후 최소 거리의 색상과 최대 거리의 색상을 추출한 후 최소-최대 색상 쌍이 이루는 각에 대한 각각의 빈도수를 계산한다. 그런 다음, 각각의 이루는 각에 대해서 최소 거리 색상에 대한 최대 거리 색상들의 평균값과 분산값으로 구성된 새로운 기술자(min-max color correlation descriptor, MMCCD)를 생성한다. 제안한 색상 기술자를 이용하여 검색한 결과는 기존 방법들과 비교했을 경우 정확률에서 최소 5.2%에서 최대 13.21% 향상된 검색 결과를 확인할 수 있었다. 또한, 국부적인 푸리에 변환에 기반한 질감 기술자를 새로운 색상 기술자와 결합하여 특징 벡터의 크기를 절반으로 줄이면서도 새로운 색상 기술자만을 사용할 경우와 비교하여 향상된 검색 결과를 확인할 수 있었다.

• 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.