• Journal of Animal Environmental Science
• /
• v.6 no.1
• /
• pp.23-30
• /
• 2000

A automated noncontact weight system for pigs consisted of a CCD-type video camera and 10 photo sensors connected to a computer. In the experiment 20 pigs(Large Yorkshire $\times$ Landrace breed) weighing from 95kg to 115kg were used. Pig's original image data was transformed to a binary image an image excluding head and tail portion from the whole binary image and the area of pig was calculated. Then pig's volume was calculated by multiplying the area by the body hight measured with photo sensors. The correlation equation between the above volume(x) and pig's weight was y=0.0007 x -9.2152($R^2$=0.9965) Performance of a automated noncontact weighing system for pigs was tested with this equation. The results showed $\pm$0.65kg average error and 1.63kg maximum error. It was concluded that performance of a automated noncontact weighing system is excellent.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.11a
• /
• pp.66-71
• /
• 2002

In Generally, a imbedding and extracting is good as watermark using a random dot image. In this paper, when the autostreogram which has some randomness is used watermark image, distortion rate is low and extraction rate is high. Using this quality, when any logo image is transformed to same image domain randomly, distortion rate is low and extraction rate is high, more over the robustness is good in spite of hard clipping.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.4
• /
• pp.1066-1071
• /
• 1998

This paper aims to examine the relationship between the directional characteristics and the quality for fingerprint image as preprocessing stage for adative image enchancement. In order to do that, we transformed the original images into directional images and set up the subimage size of 16, 32, 64 and the direction of 1, 2, 3, 4. Then we extracted the accumulated directional value as the measurement of quality for fingerprint images. By using the clustering algirthm, we performed an analytic experiemnt with the result. Finally, we could extract the optimal subimage size and directional characteristics of fingerprint image.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.410-413
• /
• 1988

In this paper, the real-time optical associative memory using multiple hologram which is generated with two angular multiplexed reference beams and Fourier transformed object beam in the $BaTiO_{3}$ crystal based on DFWM mechanism. When one image is recorded in the $BaTiO_{3}$ crystal, complete image can be recalled by 9 % partial input of the stored original image without any additional thresholding and optical feedback process. As an experimental result of multiple Fourier hologram which is recorded with two binary images, OHCHAS and PARKHK, we can obtain complete image recalled by 1/6 partial input of the stored image.

• Journal of Digital Contents Society
• /
• v.17 no.3
• /
• pp.197-202
• /
• 2016

This paper suggested that medical image database construction technique that generated and recognized from variable medical device and professional medical experts for the formalization and pattern extraction from informal medical images. And then we transformed informal image characteristics to digital data, and generated the meaningful pattern matching informations. Through this experienced works, so many related researchers can easily access the medical images database and use this formalized image informations on the variable fields.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.19 no.4
• /
• pp.21-25
• /
• 1982

This paper describes a new algorithm for the extraction of target-like objects. In order to extract target-like objects, a given image is transformed into two-valued image by thresholding, and then a double gate is applied to the two-valued image. With the synthetic-image data, we have shown the good performance of the new algorithm.

• Journal of Information Processing Systems
• /
• v.6 no.4
• /
• pp.435-452
• /
• 2010

This paper proposes a novel reversible data hiding scheme based on a Vector Quantization (VQ) codebook. The proposed scheme uses the principle component analysis (PCA) algorithm to sort the codebook and to find two similar codewords of an image block. According to the secret to be embedded and the difference between those two similar codewords, the original image block is transformed into a difference number table. Finally, this table is compressed by entropy coding and sent to the receiver. The experimental results demonstrate that the proposed scheme can achieve greater hiding capacity, about five bits per index, with an acceptable bit rate. At the receiver end, after the compressed code has been decoded, the image can be recovered to a VQ compressed image.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.1
• /
• pp.1-7
• /
• 2011

In the bomb impact test, to acquire the bomb impact point location the high-priced embedded equipments such as the Bomb Scoring System or the EOTS are needed. Recently, a high-resolution image processing could be possible since the resolution of the commercial camera is growing rapidly. In this paper we first propose an image transformation method for acquiring the real bomb impact image using a high-resolution commercial camera, and then present the process calculating the real bomb impact point location coordinate from the transformed image. Based on the experimental results we found the possibilities that the real bomb impact point information could be effectively earned just using the commercial camera.

• Korean Journal of Optics and Photonics
• /
• v.14 no.6
• /
• pp.630-635
• /
• 2003

We propose an encryption method using visual cryptography and virtual phase images. In the encryption process, the original image is shared by virtual images and the decryption key image. We multiply the virtual phase images with each complex image, which has the constant value of its sum after performing the phase modulation of the virtual images and the decryption key. The encryption cards are made by Fourier transforming the multiplied images. It is possible to protect information about the original image because the cards do not have any information from the original image. To reconstruct the original image, all the encryption cards are placed on each path of a Mach-Zehnder interferometer and then the lights passing through them are summed. Since the summed image is inverse Fourier transformed by a Fourier lens, the phase image is multiplied with the decryption key and the output image is obtained in the form of intensity on the CCD plane. Computer simulations show a good performance of the pro-posed optical security system.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.25-36
• /
• 2014

Multispectral image classification of individual tree species is often difficult because of the spectral similarity among species. In this study, we attempted to analyze the suitability of hyperspectral image to classify coniferous tree species. Several image sets and classification methods were applied and the classification results were compared with the ones from multispectral image. Two airborne hyperspectral images (AISA, CASI) were obtained over the study area in the Gwangneung National Forest. For the comparison, ETM+ multispectral image was simulated using hyperspectral images as to have lower spectral resolution. We also used the transformed hyperspectral data to reduce the data volume for the classification. Three supervised classification schemes (SAM, SVM, MLC) were applied to thirteen image sets. In overall, hyperspectral image provides higher accuracies than multispectral image to discriminate coniferous species. AISA-dual image, which include additional SWIR spectral bands, shows the best result as compared with other hyperspectral images that include only visible and NIR bands. Furthermore, MNF transformed hyperspectral image provided higher classification accuracies than the full-band and other band reduced data. Among three classifiers, MLC showed higher classification accuracy than SAM and SVM classifiers.