Earticle

로봇 네비게이션은 외부 환경요소의 지각변화를 감지하는 데 있어서 복잡하고 어려운 작업을 요구한다. 로봇 네비게이션 개발의 방법 중 하나로 로봇의 위치 변화를 검출하고 로봇에서 촬영된 이미지를 분석하는 이미지 프로세싱 기술이 있다. 촬영된 이미지는 로봇의 이동 경로에 따라 변화되는 텍스처 이미지의 변화량과 순서, 조명등의 조건 데이터를 포함하게 되고, 기존의 컴퓨팅 자원을 활용하여 이를 분석하는 경우 텍스처 이미지 시퀀스의 변화량 검출 및 인식 작업에 많은 자원의 할애와 처리 시간 증대라는 문제점이 있다. 본 논문에서는 시퀀스 이미지의 효율적인 3D 변화량 측정을 위한 클라우드 컴퓨팅 인프라 응용 방안에 대해 설명한다.

The robot navigation in outdoor environments is a daunting task as it requires the robots to sense the perceptual changes in their environment. One of the possible methods for robot navigation is to use the image processing techniques to analyze the images captured by the robot for detecting the changes in position of the robot. The images captured by the robot camera thus results in a sequence of texture image whereby the appearance of the texture changes with the motion of the robot and with changes in lighting conditions. The detection of these perceptual changes from the texture image sequence is an expensive task if conventional computing resources are utilized. This paper presents the application of a cost effective cloud computing infrastructure for the task of 3D change estimation in texture sequence images. The utilization of cloud computing infrastructure helped in providing a time efficient and real time robot navigation system.

Background: Color texture analysis was applied as a tool for quantitative evaluation of radiation- induced skin injuries. Materials and Methods: We prospectively selected 20 breast cancer patients who underwent whole-breast radiotherapy after breast-conserving surgery. Color images of skin surfaces for irradiated breasts were obtained by using a mobile skin analyzer. The first skin measurement was performed before the first fraction of radiotherapy, and the subsequent measurement was conducted approximately 10 days after the completion of the entire series of radiotherapy sessions. For comparison, color images of the skin surface for the unirradiated breasts were measured similarly. For each color image, six co-occurrence matrices (red-green [RG], red-blue [RB], and green-blue [GB] from color channels, red [R], green [G], blue [B] from gray channels) can be generated. Four textural features (contrast, correlation, energy, and homogeneity) were calculated for each co-occurrence matrix. Finally, several statistical analyses were used to investigate the performance of the color textural parameters to objectively evaluate the radiation-induced skin damage. Results and Discussion: For the R channel from the gray channel, the differences in the values between the irradiated and unirradiated skin were larger than those of the G and B channels. In addition, for the RG and RB channels, where R was considered in the color channel, the differences were larger than those in the GB channel. When comparing the relative values between gray and color channels, the ‘contrast’ values for the RG and RB channels were approximately two times greater than those for the R channel for irradiated skin. In contrast, there were no noticeable differences for unirradiated skin. Conclusion: The utilization of color texture analysis has shown promising results in evaluating the severity of skin damage caused by radiation. All textural parameters of the RG and RB cooccurrence matrices could be potential indicators of the extent of skin damage caused by radiation.

본 논문에서는 플라스틱 필름에 종이 같은 거친 질감을 부여하기위해 필름 표면에 질감 처리를 하여 인쇄된 필름 의 이미지, 거칠기 및 마찰 분석, 소비자의 주관적 부드러 움에 대한 평가를 정량화 하였다. 또한 정량 지표와 촉감 선호도 조사를 반영하여 소비자 촉감 선호도 예측 모델을 구축하였다. SEM분석에서 질감바니쉬 인쇄필름의 평균 입 자 크기가 무광인쇄필름의 평균 입자 크기보다 큰 것을 확 인하였다. 이는 질감바니쉬 처리공정에서 유색안료가 입자 의 크기를 키운 결과로 판단된다. 또한 AFM 분석에서 질 감바니쉬 인쇄필름의 대부분의 거칠기 파라미터에서 높은 거칠기를 나타내 입자크기가 거칠기에 영향을 준다는 것을 알 수 있었다. 접촉각 및 표면에너지에도 유사한 경향성이 나타났는데, 질감바니쉬 인쇄필름의 접촉각이 가장 컸고, 표 면에너지가 가장 낮았다. 이 역시 입자크기와 연관성이 있을 것으로 확인되며 인쇄성은 떨어질 것으로 예상된다. AFM을 활용한 Ra 값은 질감처리방법에 따라 데이터의 편차가 발 생하였지만, 표면 거칠음도 프로파일 파라미터에서는 실험 재현성에 있어 안정적인 파라미터인 R-MAD값 분석을 통 해 거칠음도의 차이는 유의미하지 않은 것으로 확인된다. 표면 마찰 프로파일 파라미터에서 MIU와 F-MAD의 결정 계수가 낮게 확인되어 두 파라미터는 독립적인 지표로 간 주해야 할 것으로 판단된다. 표면 거칠음도 프로파일 파라 미터와 마찰 프로파일 파라미터를 비교 분석하였을 때 표 면 거칠음도와 표면 마찰의 상관계수는 낮았으며 이에 따 라 재료의 표면 특성화에 있어 두 파라미터가 상호 독립적 으로 고려되어야 할 것으로 사료된다. SPT 수행결과와 표면 프로파일 파라미터 (GM)을 비교하 였을 때 소비자의 촉감 선호도 증진과 감성디자인 구현을 위해서는 표면 거칠음도의 영향이 지배적인 것으로 분석되 었으며 종이 질감과 유사한 질감이 구현될수록 선호도가 증 가하는 것으로 나타났다. 표면 프로파일 파라미터를 독립변 수로 사용하여 구축된 질감 선호도 예측 모델의 경우 1-P Model 와 2-P Model에 대하여 결정계수는 각각 0.945 및 0.989를 기록하여 2-P Model이 상대적으로 우수한 것으로 확인되었다. 그러나 두 모델간의 결정계수가 유사하게 측정 되었기 때문에, 분석 시간 및 입력 변수 등의 효율성을 고 려하였을 경우 거칠음도 파라미터 단독의 모델의 효용성 역 시 준수할 것이라 판단된다. 2-P Model에서 주관적인 질감 선호도 예측 기여도는 표면 거칠음도 63.9%, 마찰 프로파 일 파라미터는 36.1%로 분석 되었다. 따라서 소비자의 촉 감 선호도 향상을 위해서는 거칠음도 특성을 우선적으로 고 려해야 할 것으로 사료된다. 본 모델을 통하여 거칠음도 혹 은 마찰 특성의 조정에 따라 소비자의 포장지 질감 선호도 개선이 가능함을 확인할 수 있었다. 연구결과는 감성디자인 포장지의 인쇄 설계 및 개발을 위한 기초자료로 활용될 수 있을 것이며, 이를 다양한 질감 처리 방식에도 해당 모델을 적용하여 활용할 수 있을 것으로 기대된다.

One of the main functions of packaging is promoting the products. Competitive markets demand that products appeal more to consumers in many perspectives. Other than its original purpose, which is protection, packaging has been tasked with implementing the emotional appeal of a product through unique shapes, textures, and visual designs. Understanding emotional appeals to consumer is a potential marketing strategy so that research have been done about techniques to visualize the design and print the specific textures. Especially, paper-like films are known as eco-friendly or emotional design and they are able to protect the products from oxygen or water vapor better than papers. In this study, paper-like films, which is printed with inks to have rougher surfaces, are analysed in terms of roughness, friction, imaging and sensory evaluation of subjective softness from consumers. Also, the prediction model was established with the correlation of the measured results and sensory panel test (SPT) of consumer preferences by touch. The results showed that the prediction of subjective texture preference was contributed by 63.9% for surface roughness and 36.1% for friction profile parameters. It confirmed that surface roughness characteristics should be prioritized to improve tactile preference for paper-like films.

본 논문은 펫 휴머니제이션 현상으로 펫푸드 시장이 질적으로 고도화되었음에도, 불구하고, 여전히 「사료관 리법」상 축산 생산 수단적 관점에 머물러 있는 현행 관 리 체계의 한계를 조명하고 실증적인 물성 표준화 방안 을 제시하고자 수행되었다. 우선 KS H 4897 및 법정 관 리 체계와의 비교·분석을 통해 펫푸드 물성 규격화의 제 도적 미비점을 규명하였다. 또한, 반려견 보호자 71명을 대상으로 시행한 설문조사 결과, 응답자의 97.0%가 제품 구매 시 물성을 주요하게 고려하나 54.0%는 제조사별 다 른 마케팅 용어로 인해 선택의 어려움을 겪고 있음을 확 인하였다. 특히 단단한 제형으로 인한 치아 및 잇몸 손상 경험(15.0%)과 습식 급여 중 사레 경험(46.0%) 등 실질적 인 급여 안전사고 실태를 통해 정량적 지표 도입의 당위 성을 확보하였다. 이를 바탕으로 반려견의 해부학적 구조 와 체급별 치악력 등 수의학적 근거를 반영하여 유동식 부터 고강직식까지 아우르는 5단계의 ‘반려견 Texture-Code’를 도출하였다. 본 논문은 영양 성분에 치 중되었던 기존 품질 관리 패러다임을 물리적 섭식 안전 분야로 확장하고, 향후 반려동물의 지위 변화를 반영한 선진적 사료 관리 체계 수립을 위한 기초 자료를 제공한 다는 점에서 학술적·제도적 의의를 지닌다.

This study aims to address the limitations of the current pet food management system under the Control of Livestock and Fish Feed Act, which still views pet food as a means of livestock production despite the qualitative advancement of the market driven by Pet Humanization. Through a comparative analysis with Korean Industrial Standards for senior-friendly foods (KS H 4897) and relevant legal frameworks, the study identified institutional gaps in pet food texture standardization. A survey of 71 dog owners revealed that while 97.0% consider texture a key factor in purchasing, 54.0% experience confusion due to inconsistent marketing terms across manufacturers. Furthermore, empirical evidence of feeding safety issues, such as dental or gingival injuries (15.0%) and choking or coughing during feeding (46.0%), underscored the necessity for quantitative indicators. Based on these findings, this study proposed the "Canine Texture-Code," a five-stage quantitative framework ranging from liquid/puree to high-hardness food, incorporating veterinary evidence such as esophageal anatomy and bite force by body size. This research holds academic and institutional significance by expanding the quality control paradigm from nutrient-focused standards to physical feeding safety, providing a fundamental basis for establishing an advanced pet food management system that reflects the evolving social status of companion animals.

In this paper we are elaborating the concept of disease detection in the human body using the nail image of human fingers and analyzing the data from the image on the basis of nail color and texture. Fingernail has to be detected from the entire hand region using distribution density of the nail color pixels on the surface of nail. The methodology for creating a finger nail detection system involves removing the skin area from shiny/glossy nail portion; this is known as image segmentation concept that separates the specific object. Image segmentation is the method of dividing the image pixels into homogenous region.

In this paper we propose a new biometric-based Iris feature extraction system. The system automatically acquires the biometric data in numerical format (Iris Images) by using a set of properly located sensors. We are considering camera as a high quality sensor. Iris Images are typically color images that are processed to gray scale images. Then the Feature extraction algorithm is used to detect “IRIS Effective Region (IER)” and then extract features from “IRIS Effective Region (IER)” that are numerical characterization of the underlying biometrics. Later on this work will be helping to identify an individual by comparing the feature obtained from the feature extraction algorithm with the previously stored feature by producing a similarity score. This score will be indicating the degree of similarity between a pair of biometrics data under consideration. Depending on degree of similarity, individual can be identified.

The general edge extraction algorithm is not ideal to process infrared images, which is low contrast and blurred edge. In this paper, we used the multi-fractal spectrum to edge of infrared image. We extracted the edge information of the image and calculate the measure and fractal spectrum with multiple singular values of each pixel. Analysis of the similarities and differences of multiple measure, the function in edge extraction, meanwhile, analyzed the fiction of fractal characteristics to edge image extraction. This method differs from the traditional gradient algorithm，It determines whether the edge or not just according to the local extreme points , but according to the pixels in the local and global relationships to determine whether the pixel is a real edge. It can neglect important edge pixel and texture pixel，which is more in line with the human visual mental. It provide a good reference for recognition of infrared image and further processing.

Content-based image retrieval is a very important area of research nowadays. Content Based mage Retrieval (CBIR) is a technique which uses visual features of image such as color, shape, texture, etc. CBIR technologies provide a method to find images in large databases by using unique descriptors from a trained image. A lots of research works had been completed in the past decade to design efficient image retrieval techniques from the image or multimedia databases. Large number of retrieval techniques has been introduced, but there is no universally accepted feature extraction and retrieval technique available. In this paper, we present a study of various content-based image retrieval systems and their behaviour, texture analysis and various feature extraction with representation.

Face recognition (FR) system can automatically identify or check face image from a digital camera or image generation equipment, in order to do this, to extract facial features from images obtained, and compared with face data in the database. At present, almost all of the FR face barriers associated with facial Angle, including the lack of light and the low resolution, these problems has greatly reduce the recognition rate. In order to solve this problem, this paper proposes a face recognition framework based on the sub pattern under the condition of illumination change, first of all, the framework using minimize the total variation image of discrete cosine transform (DTV) and the Gabor filter, and combined the sub-mode analysis (SMP) and distinguish the accumulative feature transformation (DAFT), can effectively solve the face recognition problem of light conditions big change, secondly by extracting the texture characteristics of local model is not sensitive to illumination changes, using Distance transformation measures (Distance Conversion Metrics, DCM) and k-means (K-Mean) algorithm, the recognition rate of face recognition is improved effectively. The effectiveness of the method verified respectively on the two face library: ATR - Jaffe and Yale, the experimental results show that compared with other state-of-the-art methods, the proposed method in dealing with the face recognition problem under the condition of the unrestricting obtained better recognition effect.

This work presents an approach for the analysis of abnormality in the cervical cells based on Texture and presence of Hyperchromasia, which are two important morphological features based on which one can distinguish between normal and abnormal cervical cells. The proposed approach is implemented in MATLAB®, a high level, interactive environment for data visualization/analysis/computation. This may help pathologist in identification of cervical cancer from Pap smear images and help in early diagnosis.

Many textures based image retrieval researchers use global texture features for representing and retrieval of images from an image database. However, this leads to misrepresentation of local information leading to the inefficient image retrieval performance. This paper presents an approach to overcome the problem. The approach focuses on extracting local Haralick’s texture feature based on a predetermined region using the color co-occurrence matrix method, the selection of the ‘significant’ Haralik’s texture features and evaluation of the performance of the combination of the ‘significant’ features. The proposed method which is an Average Analysis and a well known method, Principal Component Analysis were applied to obtain ‘significant’ features. In order to compare the performance, a series of experiments were carried out for both methods, which is the proposed Average Analysis and the Principal Component Analysis. Experiments were performed on a 1000 selected images from the Coral image database which were divided into ten categories. Based on the experimental results, it is interesting to note that for the combination ‘significant’ features obtained from the proposed Average Analysis showed better retrieval performance compared to the Principal Component Analysis for almost all categories. This finding has an important implication in deciding the correct combination of ‘significant’ features for certain image properties. It has shown that the proposed method is able to produce less computational processing time due to a reduced amount of processing involved. The result is also compared to the previous researches and has shown an increase of an average precision from 8.5% to 26%.

In three-dimensional(3D) modeling, texturing plays a crucial role as a visual element, imparting detail and realism to models. In contrast to traditional texturing methods, the current trend involves utilizing AI tools such as Leonardo.Ai and Meshy to create textures for 3D models in a more efficient and precise manner. This paper focuses on 3D texturing, conducting a comprehensive comparative study of AI tools, specifically Leonardo.Ai and Meshy. By delving into the performance, functional differences, and respective application scopes of these two tools in the generation of 3D textures, we highlight potential applications and development trends within the realm of 3D texturing. The efficient use of AI tools in texture creation also has the potential to drive innovation and enhancement in the field of 3D modeling. In conclusion, this research aims to provide a comprehensive perspective for researchers, practitioners, and enthusiasts in related fields, fostering further innovation and development in this domain.

앰비언트 뮤직은 기존 음악의 구조적 형식을 따르지 않고, 반복적 음향에 따른 공간감 형성을 위한 음악 장르이다. 본 연구는 텍스처 중첩을 통한 앰비언트 뮤직의 구조를 분석하고 그 음악적 특징을 밝히고자 하였다. 에이펙트 트윈의 'Lichen'을 분석하여 텍스처의 중첩과 반복으로 앰비언트 뮤직의 다이내믹 구조 변화를 분석하였다. 중첩되는 텍스처를 통해 곡의 구조를 이끌어가고 있으며, 이는 공간감의 확장으로 이어진다는 것을 확인하였다. 분석을 통해 앰비언트 구조의 특징으로 반복의 구조, 텍스처의 깊이와 밀도 조절을 통한 다이내믹 구조 변화, 미세한 변화를 이용한 공간감 형성으로 결과를 제시하였다. 이러한 구조의 분석은 1990년대 후기에 등장하는 타 장르와 융합한 앰비언트 장르의 전자음악에도 적용할 수 있다. 본 연구를 통해 앰비언트 뮤직 뿐만 아니라 전통적인 형식을 지니지 않은 음악의 구조적 특징을 밝히는 가능성을 제시할 것이다.

Ambient music is a genre that does not follow the structural forms of traditional music but instead focuses on creating a sense of space through repetitive sounds. This study aimed to analyze the structure of ambient music through texture layering and clarify its musical characteristics. By analyzing Aphex Twin's "Lichen," the dynamic structural changes of ambient music were examined through the layering and repetition of textures. The overlapping textures guide the structure of the piece, confirming that this leads to an expansion of spatial perception. The analysis revealed characteristics of ambient structure, including repetitive forms, dynamic changes through control of texture depth and density, and spatial formation using subtle variations. This structural analysis can also be applied to electronic ambient genres that emerged in the late 1990s through fusion with other genres. This study suggests the potential to elucidate the structural characteristics of not only ambient music but also other music that does not possess traditional forms.

본 연구에서는 쇠라와 시냑으로 대표되는 신인상주의 작품을 대상으로, 점묘법의 도입을 통해 표현된 질감의 과학적 의미를 분석하는 방법을 제시하고 있다. 분석을 위하여 GLCM에 기반한 하라릭(Haralick) 특징 변수를 적용하였다. 하라릭 특징 변수는 질감에 대한 2차원 통계치를 추출하기위한 도구이다. 본 연구에서는 각 화가에 대하여 75개씩 질감 데이터를 랜덤하게 추출하여 20개의 특징 변수값을 측정한 후 통계적 의미를 검정하기 위하여 독립 t-검정을 수행하였다. 실험결과 두 화가의 질감에 대한 14개의 특징변수에서 유의미한 차이가 존재함을 확인할 수 있었다. 쇠라의 경우 시냑에 비해 명암도의 차이가 큰 픽셀들을 많이 사용하였으며, 이로 인해 픽셀들간의 유사성이 낮아지게 되고 변이도가 큰 질감이 느껴지게 됨을 알 수 있었다. 반면 시냑의 경우 인접한 픽셀들간의 상관성이 쇠라에 비해 높으므로 명암도의 차이가 적고 에너지와 동질성이 크므로 상대적으로 질감이 대체적으로 균일한 편임을 알 수 있었다.

This study analyze texture's scientific meaning of Neo-impressionist painters who, working with Seurat and Signac, helped develop the Pointillist style. We uses GLCM based Haralick's feature variables to analyze paintings. It is a good tool to extract 2D statistical values about painting's texture. In this study, after we randomly extract 75 texture images per painter and measure 20 feature variables, we use a independent t-test for finding statistical meanings. Throughout experimental results, we can confirm the existence of texture's differences in 14 feature variables among two painters. In comparison to Signac, Statistically significant differences are appeared between intensities. The results are confirmed that has the low-similarity between pixels. And it is known that texture have large variability. In the case of Signac, on the other hand, because texture correlation between adjacent pixels have high relative intensity, so texture is generally uniform.

In cosmetic formulations, texture plays a key role in ingredient choice and formulation optimization. But texture parameters are often measured by sensorial analysis in the last stages of formulation development. Rheology or texture analysis, used separately, has the benefit of characterizing the behavior of raw materials (e.g. polymers) and controlling and predicting the stability of formulations. SEPPIC has developed rheology and texture analysis protocols to obtain a better understanding of the influence of raw materials on the cosmetic texture of formulations. When used in combination, these two methodologies are complementary and provide useful data regarding the impact of raw material choice on all the development steps: manufacturing procedure, formulation stability, skin feeling.

텍스처 이미지가 다양한 산업 애플리케이션 분야에 널리 사용됨에 따라, 이러한 이미지들의 저작권 보호는 중요한 이슈가 되어왔다. 이러한 이유로, 본 논문은 이미지에 내재한 텍스처 특성을 이용한 칼라 텍스처 이미지 워터마킹 알고리즘을 제안한다. 제안한 알고리즘은 퍼지 클러스터링을 위한 입력으로써 그레이 레벨 동시발생 행렬의 에너지와 동질성 특징을 사용하여 워터마크를 삽입하기 위한 적당한 블록들을 선택한다. 워터마크를 삽입하기 위해 먼저 선택된 블록들에 이산 웨이블릿 변환을 수행하고, 이산 웨이블릿 변환의 서버밴드들의 하나를 선택한다. 그런후에 이 워터마크를 중간 대역의 이산 코사인 변환 계수에 삽입한다. 또한, 본 논문은 워터마크 삽입 후 비인지성과 다양한 형태의 워커마킹 공격에 대해 강인성이 뛰어난 이득 계수들과 이산 웨이블릿 변환의 서버밴드들의 효과를 탐색한다. 모의실험 결과, 제안한 알고리즘은 이득 계수가 42이고 HH 밴드에 워터마크를 삽입하였을 때 높은 PSNR 값 (47.66 dB to 48.04 dB) 및 낮은 M-SVD 값 (8.84 to 15.6)을 얻었다. 또한 제안한 알고리즘은 노이즈 첨가, 필터링, 잘라내기 및 JPEG 압축과 같은 다양한 이미지 처리 공격에서도 높은 상관 값 (0.7193 to 1)을 보였다.

As texture images have become prevalent throughout a variety of industrial applications, copyright protection of these images has become important issues. For this reason, this paper proposes a color-texture image watermarking algorithm utilizing texture properties inherent in the image. The proposed algorithm selects suitable blocks to embed a watermark using the energy and homogeneity properties of the grey level co-occurrence matrices as inputs for the fuzzy c-means clustering algorithm. To embed the watermark, we first perform a discrete wavelet transform (DWT) on the selected blocks and choose one of DWT subbands. Then, we embed the watermark into discrete cosine transformed blocks with a gain factor. In this study, we also explore the effects of the DWT subbands and gain factors with respect to the imperceptibility and robustness against various watermarking attacks. Experimental results show that the proposed algorithm achieves higher peak signal-to-noise ratio values (47.66 dB to 48.04 dB) and lower M-SVD values (8.84 to 15.6) when we embedded a watermark into the HH band with a gain factor of 42, which means the proposed algorithm is good enough in terms of imperceptibility. In addition, the proposed algorithm guarantees robustness against various image processing attacks, such as noise addition, filtering, cropping, and JPEG compression yielding higher normalized correlation values (0.7193 to 1).

We investigated whether the CT images of hepatic lesions could be analyzed by computer-aided diagnosis (CAD) tool. We retrospectively reanalyzed 14 liver CT images (10 hepatocellular cancers and 4 benign liver lesions; patients who presented with hepatic masses). The hepatic lesions on CT were segmented by rectangular ROI technique and the morphologic features were extracted and quantitated using fractal texture analysis. The contrast enhancement of hepatic lesions was also quantified and added to the differential diagnosis. The best discriminating function combining the textural features and the values of contrast enhancement of the lesions was created using linear discriminant analysis. Textural feature analysis showed moderate accuracy in the differential diagnosis of hepatic lesions, but statistically insignificant. Combining textural analysis and contrast enhancement value resulted in improved diagnostic accuracy, but further studies are needed.

Worldwide trends in animal welfare have resulted in an increased interest in individual management of sows housed in groups within hog barns. Estrus detection has been shown to be one of the greatest determinants of sow productivity. Purpose: We conducted this study to develop a method that can automatically detect the estrus state of a sow by selecting optimal texture parameters from images of a sow's pudendum and by optimizing the number of neurons in the hidden layer of an artificial neural network. Methods: Texture parameters were analyzed according to changes in a sow's pudendum in estrus such as mucus secretion and expansion. Of the texture parameters, eight gray level co-occurrence matrix (GLCM) parameters were used for image analysis. The image states were classified into ten grades for each GLCM parameter, and an artificial neural network was formed using the values for each grade as inputs to discriminate the estrus state of sows. The number of hidden layer neurons in the artificial neural network is an important parameter in neural network design. Therefore, we determined the optimal number of hidden layer units using a trial and error method while increasing the number of neurons. Results: Fifteen hidden layers were determined to be optimal for use in the artificial neural network designed in this study. Thirty images of 10 sows were used for learning, and then 30 different images of 10 sows were used for verification. Conclusions: For learning, the back propagation neural network (BPN) algorithm was used to successful estimate six texture parameters (homogeneity, angular second moment, energy, maximum probability, entropy, and GLCM correlation). Based on the verification results, homogeneity was determined to be the most important texture parameter, and resulted in an estrus detection rate of 70%.

Breast ultrasonic reading is critical as a primary screening test for the early diagnosis of breast cancer. However, breast ultrasound examinations show significant differences in diagnosis based on the difference in image quality according to the ultrasonic equipment, experience, and proficiency of the examiner. Accordingly, studies are being actively conducted to analyze the texture characteristics of normal breast tissue, positive tumors, and malignant tumors using breast ultrasonography and to use them for computer-assisted diagnosis. In this study, breast ultrasonography was conducted to select 247 ultrasound images of 71 normal breast tissues, 87 fibroadenomas among benign tumors, and 89 malignant tumors. The selected images were calculated using a statistical method with 21 feature parameters extracted using the gray level co-occurrence matrix algorithm, and classified as normal breast tissue, benign tumor, and malignancy. In addition, we proposed five feature parameters that are available for computer-aided diagnosis of breast cancer classification. The average classification rate for normal breast tissue, benign tumors, and malignant tumors, using this feature parameter, was 82.8%.