• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.40-47
• /
• 2009

This paper proposes a method for vehicle license plate detection using mathematical morphology and symmetry. In general, the shape, color, size, and position of license plate are regulated by authorities for a better recognition by human. Among them, the relatively big intensity difference between the letter and the background region of the license plate and the symmetry about the plate are major discriminating factors for the detection. For the first, the opened image is subtracted from the closed image to intensify the region of plate using the rectangular structuring element which has the width of the distance between two characters. Second the subtraction image is average filtered with the mask size of the plate. Third, the column maximum graph of the average filtered image is acquired and the symmetry of the graph is measured at every position. Fourth, the peaks of the average filtered image are searched. Finally, the plate is assumed to be positioned around the one of local maxima nearest to the point of the highest symmetry. About 1,000 images taken by speed regulation camera are used for the experiment. The experimental result shows that the plate detection rate is about 93%.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1109-1124
• /
• 2022

This study proposes a marine debris monitoring methods using satellite and drone multispectral images. A multi-layer perceptron (MLP) model was applied to detect marine debris using Sentinel-2 satellite image. And for the detection of marine debris using drone multispectral images, performance evaluation and comparison of U-Net, DeepLabv3+ (ResNet50) and DeepLabv3+ (Inceptionv3) among deep learning models were performed (mIoU 0.68). As a result of marine debris detection using satellite image, the F1-Score was 0.97. Marine debris detection using drone multispectral images was performed on vegetative debris and plastics. As a result of detection, when DeepLabv3+ (Inceptionv3) was used, the most model accuracy, mean intersection over union (mIoU), was 0.68. Vegetative debris showed an F1-Score of 0.93 and IoU of 0.86, while plastics showed low performance with an F1-Score of 0.5 and IoU of 0.33. However, the F1-Score of the spectral index applied to generate plastic mask images was 0.81, which was higher than the plastics detection performance of DeepLabv3+ (Inceptionv3), and it was confirmed that plastics monitoring using the spectral index was possible. The marine debris monitoring technique proposed in this study can be used to establish a plan for marine debris collection and treatment as well as to provide quantitative data on marine debris generation.

• Journal of Korea Multimedia Society
• /
• v.8 no.7
• /
• pp.898-905
• /
• 2005

Iris recognition Is that identifies a user based on the unique iris muscle patterns which has the functionalities of dilating or contracting pupil region. Because it is reported that iris recognition is more accurate than other biometries such as face, fingerprint, vein and speaker recognition, iris recognition is widely used in the high security application domain. However, if unnecessary information such as eyelid and eyelash is included in iris region, the error for iris recognition is increased, consequently. In detail, if iris region is used to generate iris code including eyelash and eyelid, the iris codes are also changed and the error rate is increased. To overcome such problem, we propose the method of detecting eyelid by using pyramid searching parabolic deformable template. In addition, we detect the eyelash by using the eyelash mask. Experimental results show that EER(Equal Error Rate) for iris recognition using the proposed algorithm is lessened as much as $0.3\%$ compared to that not using it.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.12
• /
• pp.71-83
• /
• 1996

This paper describes facial component detection and skew correction algorithm for face recognition. We use a priori knowledge and models about isolated regions to detect eye location from the face image captured in natural office environments. The relations between human face components are represented by several rules. We adopt an edge detection algorithm using sobel mask and 8-connected labelling algorith using array pointers. A labeled image has many isolated components. initially, the eye size rules are used. Eye size rules are not affected much by irregular input image conditions. Eye size rules size, and limited in the ratio between gorizontal and vertical sizes. By the eye size rule, 2 ~ 16 candidate eye components can be detected. Next, candidate eye parirs are verified by the information of location and shape, and one eye pair location is decided using face models about eye and eyebrow. Once we extract eye regions, we connect the center points of the two eyes and calculate the angle between them. Then we rotate the face to compensate for the angle so that the two eyes on a horizontal line. We tested 120 input images form 40 people, and achieved 91.7% success rate using eye size rules and face model. The main reasons of the 8.3% failure are due to components adjacent to eyes such as eyebrows. To detect facial components from the failed images, we are developing a mouth region processing module.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.233-238
• /
• 2005

With iris recognition algorithm, unique iris code can be generated and user can be identified by using iris pattern. However, if unnecessary information such as eyelash is included in iris region, the error for iris recognition is increased, consequently. In detail, if iris region is used to generate ins code not excluding eyelash and the position of eyelash is moved, the iris codes are also changed and the error rate is increased. To overcome such problem, we propose the method of detecting eyelash by using mask and excluding the detected eyelash region in case of generating iris code. Experimental results show that EER(Equal Error Rate) for iris recognition using the proposed algorithm is lessened as much as $0.18\%$ compared to that not using it.

• The KIPS Transactions:PartB
• /
• v.12B no.5 s.101
• /
• pp.543-552
• /
• 2005

This paper proposes the extraction of coronary arteries based on DSA(Digital Subtraction Angiography) through a texture analysis of background in the angiography. DSA is a well established modality for the visualization of coronary arteries. DSA involves the subtraction of a mask image - an image of the heart before injection of contrast medium - from live image. However, this technique is sensitive to the movement of background and can result to a wrong detection by the variance of background gray-level intensity between two images. Therefore, this paper solves a structural problem resulted from a background movement bV selecting an image which has the least difference of movement through an analysis of the similarity of background texture and proposes a method to extract only the blood vessel efficiently through local gray-level correction of the selected image. Using the coronary angiogram of 5 patients clinical data, we proved that the proposed method has the lower false-detection rate, approximately $2\%$, and the higher accuracy than the existing methods.

• Korean Journal of Optics and Photonics
• /
• v.22 no.4
• /
• pp.198-203
• /
• 2011

We have conducted a theoretical study to improve the detection limit of a surface plasmon resonance (SPR) sensor by co-localizing plasmonic fields and target molecules of interest. The fields were localized by nanograting antennas, while target molecules that participate in a molecular interaction were assumed to be co-localized by angled evaporation of a dielectric mask layer on the nanograting antennas. We have performed the evaluation using an overlap integral between distributions of plasmon fields and molecules and confirmed the correlation of the overlap with the sensitivity of an SPR sensor. Based on the calculated sensor characteristics, it was found that the sensitivity, if the fields and molecules are co-localized, can be as much as ten times that of non-colocalized structure.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.681-688
• /
• 2002

This paper proposes a system detecting the area of traffic sign, which uses color rate as the information of colors, and corner point and distance rate as the information of morphology. In this system, a candidate area is extracted by performing dilation operation on the binary image made by the color rate of R, G, B components and by detecting corner point and center point through mask. The area of traffic sign with varied shapes is extracted by calculating the distance rate from center point, which is the information of morphology. The results of this experiment demonstrate that in this system which is invariable regardless of its size and location, it is possible to extract the exact area from varied traffic signs such as the shapes of triangle, circle, inverse triangle, and square as well as from the images at both day and night when brightness value is greatly different. Moreover, it demonstrates great accuracy and speed in processing.

• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.113-126
• /
• 2009

With high temporal resolution, four times receiving during a day, MODIS images from Terra and Aqua satellites provide several advantages for monitoring spacious land. Especially, diverse MODIS products related to land, atmosphere, and ocean have been provided with radiance MODIS images. The products such as surface reflectance, NDVI, cloud mask, aerosol etc. are based on theoretical algorithms developed in academic areas. Comparing with other change detection studies mainly using the vegetation index, this study investigated temporal surface reflectance of landcovers for five years from 2004 to 2008. The near infrared (NIR) reflectance in urbanized and burned areas showed considerable difference before and after events. The specific characteristics of surface reflectance temporal profiles are possibly useful for the detection of landcover changes and classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.637-644
• /
• 2021

In general, in the fields of computer vision, robotics, and augmented reality, the importance of 3D space and 3D object detection and recognition technology has emerged. In particular, since it is possible to acquire RGB images and depth images in real time through an image sensor using Microsoft Kinect method, many changes have been made to object detection, tracking and recognition studies. In this paper, we propose a method to improve the quality of 3D reconstructed images by processing images acquired through a depth-based (RGB-Depth) camera on a multi-view camera system. In this paper, a method of removing noise outside an object by applying a mask acquired from a color image and a method of applying a combined filtering operation to obtain the difference in depth information between pixels inside the object is proposed. Through each experiment result, it was confirmed that the proposed method can effectively remove noise and improve the quality of 3D reconstructed image.