• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권9호
• /
• pp.4510-4526
• /
• 2017

Most available methods of facial gender recognition work well under a constrained situation, but the performances of these methods have decreased significantly when they are implemented under unconstrained environments. In this paper, a method via low-rank and collaborative representation is proposed for facial gender recognition in the wild. Firstly, the low-rank decomposition is applied to the face image to minimize the negative effect caused by various corruptions and dynamical illuminations in an unconstrained environment. And, we employ the collaborative representation to be as the classifier, which using the much weaker $l_2-norm$ sparsity constraint to achieve similar classification results but with significantly lower complexity. The proposed method combines the low-rank and collaborative representation to an organic whole to solve the task of facial gender recognition under unconstrained environments. Extensive experiments on three benchmarks including AR, CAS-PERL and YouTube are conducted to show the effectiveness of the proposed method. Compared with several state-of-the-art algorithms, our method has overwhelming superiority in the aspects of accuracy and robustness.

• 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.

• 전자공학회논문지S
• /
• 제34S권2호
• /
• pp.63-70
• /
• 1997

This paper proposes a new algorithm for recognizing polyhedral objects using a single 2-D image. It is base don a new representation scheme having two level hierarchey. In the lower level, geometrical features of each primitive surface are represented using their signatures and the variation of signature due to rotation is represented suing the rotation map. In the higher level, topological features are represented in the inter-surface description table(SDT). Based on the proposed representaton scheme, loer level database searched to find a matching primitive surface. The srotation map determines the degree of rotation as well as the matchness. If all surfaces in a test object find their matching primitive surfaces, its structural information is compared with the SDTs of object models. If primitive surfaces of a test object equal to tha tof certain model and satisfy inter-surfaces relationship in SDT, a test object is recognized as the model.

• 전기전자학회논문지
• /
• 제17권4호
• /
• pp.478-483
• /
• 2013

본 논문은 영상 표현의 동적영역 증대를 위한 적응적 Retinex 알고리즘에 대하여 제안한다. 제안 방식은 Retinex 알고리즘을 기반으로 비대칭도를 이용하여 입력 영상에 대한 밝기 정보의 왜곡을 검출하고 왜곡 성분을 국부 통계 특성을 기반으로 적응적으로 처리하였다. 특히 휘도성분에 대하여 새로운 보정함수를 적용시킴으로써 동적영역 확대를 통해 해상도를 개선하였다. 실험을 통해 휘도 성분에 대한 동적 영역 확대 및 색 왜곡 효과를 감소시키는 효과를 확인할 수 있었다.

• 한국초등과학교육학회지:초등과학교육
• /
• 제26권5호
• /
• pp.475-488
• /
• 2007

The purpose of this study was to investigate elementary students' difficulties when they read the illustrations on scientific textbook. 5 illustrations were selected on basis that they had some of the textual/graphical features. The data were collected from open-ended questionnaires and follow-up interviews. To investigate difficulties of reading illustrations, 100 sixth grade students participated in this study and interviews were taken to 9 volunteers among those participants. The results showed that many students had difficulties in the integration of verbal representation and realistic image representation on the illustration, therefore they often misunderstood the meaning of illustration. These results gave several recommendations when we used illustrations as educational materials. Teachers would be better to guide that students could understand illustrations with the integration of the reading of one or more representations.

• 대한전기학회논문지
• /
• 제39권7호
• /
• pp.757-764
• /
• 1990

The purpose of this study is to process binary images of Breadth First Linear Quadtree in hardware. Inthis paper, we designed and verified logic level circuit of ASIC for the encoding part of the binary image that is to convert the binary image into the representation of the Breadth First Linear Quadtree. The logic level circuit is composed of cells in TTL library. The significance of thes study is to implement an algorithm by hardware rather than by software, so that the processing time can be reduced by about 20 times.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.84-85
• /
• 2019

MPEG-NNR (Compression of Neural Network for Multimedia Content Description and Analysis) aims to define a compressed and interoperable representation of trained neural networks. In this paper, we present a low-rank approximation to compress a CNN used for image compression, which is one of MPEG-NNR use cases. In the presented method, the low-rank approximation decomposes one 2D kernel matrix of weights into two 1D kernel matrix values in each convolution layer to reduce the data amount of weights. The evaluation results show that the model size of the original CNN is reduced to half as well as the inference runtime is reduced up to about 30% with negligible loss in PSNR.

• 영미문화
• /
• 제14권1호
• /
• pp.269-286
• /
• 2014

The Pre-Raphaelite oeuvre abounds in the image of women, which indicates the impact of gender question on contemporary visual culture. The representation of women in their art tends to evince the entrenched myth of womanhood, marked by a stereotyped dichotomy in the apprehension of femininity. Yet there are a significant number of pictures which attest to the point that their iconography of womanhood cannot be fully elucidated by exploring the dichotomy alone. They falsify the dyadic model, defying the attempt to accommodate them in a clean-cut category. The curious blend of the mystical, the sensual, and the domestic that characterizes these images suggests that they are open to multiple interpretations. In sum, the Pre-Raphaelite representation of women both endorses and challenges the ideal of femininity, indicating that it was shaped by and shaped contemporary perceptions of women at a time when gender relations were shifting and the traditional institution of patriarchy revealed a sign of strain.

• Journal of information and communication convergence engineering
• /
• 제8권2호
• /
• pp.185-190
• /
• 2010

In this paper we propose the CBIR algorithm which is based on a novel image block method that combined both color and edge feature. The main drawback of global histogram representation is dependent of the color without spatial or shape information, a new image block method that divided the image to 8 related blocks which contained more information of the image is utilized to extract image feature. Based on these 8 blocks, histogram equalization and edge detection techniques are also used for image retrieval. The experimental results show that the proposed image block method has better ability of characterizing the image contents than traditional block method and can perform the retrieval system efficiently.

• 제어로봇시스템학회논문지
• /
• 제8권6호
• /
• pp.455-461
• /
• 2002

Object-based image retrieval method is addressed. A new image segmentation algorithm and image comparing method between segmented objects are proposed. For image segmentation, color and texture features are extracted from each pixel in the image. These features we used as inputs into VQ (Vector Quantization) clustering method, which yields homogeneous objects in terns of color and texture. In this procedure, colors are quantized into a few dominant colors for simple representation and efficient retrieval. In retrieval case, two comparing schemes are proposed. Comparing between one query object and multi objects of a database image and comparing between multi query objects and multi objects of a database image are proposed. For fast retrieval, dominant object colors are key-indexed into database.