Sung-Hwan Jung

Image Processing-Based Fire Detection System Using Statistic Color Model

Most of fire detection system used the heuristic fixed threshold values in their specific methods. However, input images may be changed, in general, so the heuristic fixed threshold values used in the fire detection systems might be modified on a case by case basis. In this paper, an automatic fire detection system without the heuristic fixed threshold values was studied. We presented an automatic method using the statistical color model and the binary background mask. We did the experiment using 600 frames from 6 typical different fire video clips. As the experimental results the proposed method showed a good performance of about average 85% detection rate without false positive, compared with the other methods with the heuristic fixed threshold values.

A New Watermark-embedded Image Generation for Display-capture based Mobile Watermarking

Most of existing watermarking technologies are related with the research of robust watermarking for copyright protection or with the research of fragile watermarking for an authentication. Therefore, most of existing watermarking schemes use an original image for embedding a watermark and focus on imperceptibility of the watermark. The proposed mobile watermarking scheme is a new concept for embedding, which uses the generated image instead of a given original image. It generates a proper MMB (Mobile Merchandise Bond) image for the watermark to be inserted. As experimental result, we could generate the MMB image and extract MMB information from the image, the watermark-embedded image, captured by the PC camera. So we could confirm availability of the generation of the watermark-embedded image in the display-capture environments.

Coin Calculation System Using Binarization and Hue Histogram

This research proposes a new system for calculating the total amount of coins in an image. The proposed system identified and classified the coins in the image in realtime. The image was obtained using a USB camera. Most previous coin calculation systems only used size information. If the size of an object was incorrectly detected, it caused a misclassification. Especially, in case of the former 10 won, it had high error rate because it was similar in size to the 50 won and 100 won coin. The proposed system combines hue histogram information with size information to reduce errors in the classification process. When we only used size information in the classification experiment of 2,290 coins, the recognition rate was on average about 88.2%. When we combined hue information with size information the recognition rate increased to about 99.3%.

A new display-capture based mobile watermarking system

In this paper, we propose a new display-capture based mobile watermarking scheme that basically uses a generated image for watermark embedding. The proposed scheme is a new mobile watermarking concept. Instead of using a given original image in the conventional watermarking, it uses a proper generated image for inserting information. Some image distortions may occur in the display-capture environment of a mobile phone. They make a problem in the watermark decoding process. To solve the problem, we use hardware and software approaches and also model the image distortion that usually may happen in the mobile phone. As experimental result, we could embed typical MMB (Mobile Merchandise Bond) information into the background image and generate a watermark-embedded image. With preprocessing to reduce distortions, we could extract the inserted information from the watermark-embedded image captured by a PC camera. Therefore, we could confirm availability of a new mobile watermarking in the display-capture environment.