• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.222-224
• /
• 2022

Deep learning-based computer vision applications in the field of object segmentation take a transfer learning method using hyperparameters and models pretrained and distributed by STOA techniques to improve performance. Custom datasets used in this process require a lot of resources, such as time and labeling, in labeling tasks to generate Ground Truth information. In this paper, we present an automatic labeling construction method using object segmentation techniques so that resources such as time and labeling can be used less to build custom datasets used in deep learning neural networks.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.151-160
• /
• 2023

Breast cancer is the most dangerous and deadly form of cancer. Initial detection of breast cancer can significantly improve treatment effectiveness. The second most common cancer among Indian women in rural areas. Early detection of symptoms and signs is the most important technique to effectively treat breast cancer, as it enhances the odds of receiving an earlier, more specialist care. As a result, it has the possible to significantly improve survival odds by delaying or entirely eliminating cancer. Mammography is a high-resolution radiography technique that is an important factor in avoiding and diagnosing cancer at an early stage. Automatic segmentation of the breast part using Mammography pictures can help reduce the area available for cancer search while also saving time and effort compared to manual segmentation. Autoencoder-like convolutional and deconvolutional neural networks (CN-DCNN) were utilised in previous studies to automatically segment the breast area in Mammography pictures. We present Automatic SegmenAN, a unique end-to-end adversarial neural network for the job of medical image segmentation, in this paper. Because image segmentation necessitates extensive, pixel-level labelling, a standard GAN's discriminator's single scalar real/fake output may be inefficient in providing steady and appropriate gradient feedback to the networks. Instead of utilising a fully convolutional neural network as the segmentor, we suggested a new adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local attributes that collect long- and short-range spatial relations among pixels. We demonstrate that an Automatic SegmenAN perspective is more up to date and reliable for segmentation tasks than the state-of-the-art U-net segmentation technique.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.135-144
• /
• 2003

A method for the automatic segmentation of speech signals is described. The method is dedicated to the construction of a large database for a Text-To-Speech (TTS) synthesis system. The main issue of the work involves the refinement of an initial estimation of phone boundaries which are provided by an alignment, based on a Hidden Market Model(HMM). Multi-layer perceptron (MLP) was used as a phone boundary detector. To increase the performance of segmentation, a technique which individually trains an MLP according to phonetic transition is proposed. The optimum partitioning of the entire phonetic transition space is constructed from the standpoint of minimizing the overall deviation from hand labelling positions. With single speaker stimuli, the experimental results showed that more than 95% of all phone boundaries have a boundary deviation from the reference position smaller than 20 ms, and the refinement of the boundaries reduces the root mean square error by about 25%.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.215-222
• /
• 2002

This paper presents a reliable fully automatic labeling system which fits well with languages having well-developed syllables such as in Korean. The ASL System utilize DAC (Divide and Conquer), a control mechanism, based segmentation algorithm to use phonetic and acoustic information with greater efficiency. The segmentation algorithm is to devide speech signals into speechlets which is localized speech signal pieces and to segment each speechlet for speech boundaries. While HMM method has uniform and definite efficiencies, the suggested method gives framework to steadily develope and improve specified acoustic knowledges as a component. Without using statistical method such as HMM, this new method use only phonetic-acoustic information. Therefore, this method has high speed performance, is consistent extending the specific acoustic knowledge component, and can be applied in efficient way. we show experiment result to verify suggested method at the end.

• Land and Housing Review
• /
• v.14 no.4
• /
• pp.95-102
• /
• 2023

Numerous investigations have explored the integration of machine leaning algorithms with high-resolution drone image for object detection in urban settings. However, a prevalent limitation in vehicle extraction studies involves the reliance on bounding boxes rather than instance segmentation. This limitation hinders the precise determination of vehicle direction and exact boundaries. Instance segmentation, while providing detailed object boundaries, necessitates labour intensive labelling for individual objects, prompting the need for research on automating unsupervised instance segmentation in vehicle extraction. In this study, a novel approach was proposed for vehicle extraction utilizing unsupervised SVM classification applied to vehicle bounding boxes in drone images. The method aims to address the challenges associated with bounding box-based approaches and provide a more accurate representation of vehicle boundaries. The study showed promising results, demonstrating an 89% accuracy in vehicle extraction. Notably, the proposed technique proved effective even when dealing with significant variations in spectral characteristics within the vehicles. This research contributes to advancing the field by offering a viable solution for automatic and unsupervised instance segmentation in the context of vehicle extraction from image.

• Journal of Satellite, Information and Communications
• /
• v.11 no.2
• /
• pp.14-17
• /
• 2016

This paper describes the implementation of automatic number-braille converter based on image processing for the blind people. The algorithm is consists of four main steps. First step is binary image conversion of the input image obtained by the camera. the second step is segmentation operation by means of dilation and labelling of the character. Next step is calculation of cross-correlation between segmented text image and pre-defined text-pattern image. The final step is generation of brail output which is relevant to input image. The computer simulation result was showing 91.8% correct conversion rate for arabian numbers which is printed in A4-sheet and practical possibility was also confirmed by using implemented automatic number-braille converter based on DSP image processing board.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.42-42
• /
• 2017

Prediction of rice yield during a growing season would be very helpful to magnify rice yield as it also allows better farm practices to maximize yield with greater profit and lesser costs. UAV imagery based automatic detection of rice can be a relevant solution for early prediction of yield. So, we propose an image processing technique to predict rice yield using low altitude UAV images. We proposed $L^*a^*b^*$ color space based image segmentation algorithm. All images were captured using UAV mounted RGB camera. The proposed algorithm was developed to find out rice grain area from the image background. We took RGB image and applied filter to remove noise and converted RGB image to $L^*a^*b^*$ color space. All color information contain in both $a^*$ and $b^*$ layers and by using k-mean clustering classification of these colors were executed. Variation between two colors can be measured and labelling of pixels was completed by cluster index. Image was finally segmented using color. The proposed method showed that rice grain could be segmented and we can recognize rice grains from the UAV images. We can analyze grain areas and by estimating area and volume we could predict rice yield.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.351.2-356
• /
• 1998

음소 단위로 레이블링된 데이터베이스는 음성연구에 있어 매우 중요하다. 그러나 수작업에 의한 음소분할 및 레이블링 작업은 많은 시간과 노력이 필요하기 때문에 자동 음소분할 및 레이블링 시스템에 대한 많은 연구가 진행되고 있다. 본 논문에서는 monophone과 triphone의 장점을 포함하는 문맥 종속 반음소 단위 모델을 이용한 자동 음소분할 및 레이블링 시스템을 구현하였다. 레이블링 단위로는 68개의 유사음소와 묵음 등 총 69개로 정하였으며, 음소 모델링은 연속 HMM을 사용하였다. 기존의 subword 단위모델과 본 논문에서 제안한 문맥종속 반음소 모델을 이용한 자동 음소분할 및 레이블링 시스템의 성능 비교 음소경계오차가 10ms 이내인 경우 각각 60.17%, 66.32%를 포함하여 6.15%의 향상을 보이고, 40ms 이내인 경우 90.36%, 94.27%를 포함하여 3.92%의 성능향상을 보였다.