• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1149-1155
• /
• 2012

In this paper, we propose cause diagnosis method of semiconductor defects from semiconductor industrial images. Our method constructs feature database (DB) of defect images. Then, defect and input images are subdivided by uniform block. And the block similarity is measured using histogram kai-square distance after color histogram calculation. Then, searched blocks in each image are merged into connected objects using clustering. Finally, the most similar defect image from feature DB is searched with the defect cause by measuring cluster similarity based on features of each cluster. Our method was validated by calculating the search accuracy of n output images having high similarity. With n = 1, 2, 3, the search accuracy was measured to be 100% regardless of defect categories. Our method could be used for the industrial applications.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.147-154
• /
• 2008

First, this paper compute difference value between frames using the composed method of $X^2$ histogram and color histogram and the normalization. Next, cluster representative frame was decided by using the clustering for distance and the k-mean grouping. Finally, representative frame of group was decided by using the likelihood ratio. Proposed method can be known by experiment as outstanding of detection rather than other methods, due to computing of difference value, clustering and grouping, and detecting of representative frame.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.1
• /
• pp.75-80
• /
• 2008

This paper proposes a method to detect scene change using global decision tree that extract boundary cut that have width of big change that happen by camera brake from difference value of frames. First, calculate frame difference value through regional X2-histogram and normalization, next, calculate distance between difference value using normalization. Shot boundary detection is performed by compare global threshold distance with distance value for two adjacent frames that calculating global threshold distance based on distance between calculated difference value. Global decision tree proposed this paper can detect easily sudden scene change such as motion from object or camera and flashlight.

• The Journal of Korea Robotics Society
• /
• v.12 no.2
• /
• pp.217-227
• /
• 2017

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x-axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.

• Korean Journal of Digital Imaging in Medicine
• /
• v.14 no.2
• /
• pp.39-46
• /
• 2012

Purpose : The purpose of this study was to reduce Entrance Surface Dose and maintain image quality by changing Source to Image receptor Distance. And we'd like to compare ESD on this study to DRLs in other contries. Materials and Methods : We used indirect DR system(Definium 8000, General Electric, USA)and phantom(ART-200X, Flukebiomedical, USA),glass dosimeters(GD-352M, Asahi Techno Glass, Japan)for this study. The imagies were obtained throuh 80kVp fixed, and different tube currents using AEC mode in $16{\times}16$(inch) field size and changing Source to Image receptor Distance from 100 cm to 130 cm per 10 cm unit. The phantom with attaching 5 glass dosimeters on abdomonal skin was set at supine and erect position as a anterioposterial projection on detector For measuring Entrance Surface Dose. Image analysis was conducted by histograms of Image J(1.46r) which was given from National Institutes of Health(NIH). Results : Due to inverse square law of distance, the tube currents were increasing 42.6 % in supine position and 32.6 % in erect position according to the change of Source to Image receptor Distance. While Entrance Surface Doses were rapidly decreasing 14.2 % in supine position and 29.4 % in erect position according to the change of Source to Image receptor Distance. As the results of histogram using Image J, pixel mean values from 100 cm to 110 cm, 120 cm and 130 cm were decreasing each 1.4%, 2.5%, 2.7%, 4.5%, 2.2 %, 5.8 % in supine, erect position. While standard deviations from 100 cm to 110 cm, 120 cm and 130 cm were increasing each 1.4 %, 2.5 %, 2.5 %, 4.0 %, 2.0 %, 4.9 % Consequently, there are no significant differences in abdomen images taken. Conclusion: As the results described above, we strongly recommend using long Sourceto Image receptor Distance than 100cm that we have been using. So, we should deliver less Entrance Surface Dose to the patients while maintaining image quality in abdomen radiography.

• Journal of Biosystems Engineering
• /
• v.27 no.2
• /
• pp.151-160
• /
• 2002

Cow image processing technique would be useful not only for recognizing an individual but also for establishing the image database and analyzing the shape of cows. A cow (Holstein) has usually the unique speckle pattern. In this study, the individual recognition of cow was carried out using the speckle pattern and the content-based image retrieval technique. Sixty cow images of 16 heads were captured under outdoor illumination, which were complicated images due to shadow, obstacles and walking posture of cow. Sixteen images were selected as the reference image for each cow and 44 query images were used for evaluating the efficiency of individual recognition by matching to each reference image. Run-lengths and positions of runs across speckle area were calculated from 40 horizontal line profiles for ROI (region of interest) in a cow body image after 3 passes of 5$\times$5 median filtering. A similarity measure for recognizing cow individuals was calculated using Euclidean distance of normalized G-frame histogram (GH). normalized speckle run-length (BRL), normalized x and y positions (BRX, BRY) of speckle runs. This study evaluated the efficiency of individual recognition of cow using Recall(Success rate) and AVRR(Average rank of relevant images). Success rate of individual recognition was 100% when GH, BRL, BRX and BRY were used as image query indices. It was concluded that the histogram as global property and the information of speckle runs as local properties were good image features for individual recognition and the developed system of individual recognition was reliable.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.149-158
• /
• 2004

This study proposes a method for segmentation and recognition of traffic signs using shape information and edge image in real image. It first segments traffic sign candidate regions by connected component algorithm from binary images, obtained by utilizing the RGB color ratio of each pixel in the image, and then extracts actual traffic signs based on their symmetries on X- and Y-axes. Histogram equalization is performed for unsegmented candidate regions caused by low contrast in the image. In the recognition stage, it utilizes shape information including projection profiles on X- and Y-axes, moment, and the number of crossings and distance which concentric circular patterns and 8-directional rays from region center intersects with edges of traffic signs. It finally performs recognition by measuring similarity with the templates in the database. It will be shown from several experimental results that the system is robust to environmental factors, such as light and weather condition.