• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.11-17
• /
• 2023

This paper proposes a lightweight deep learning network for detecting an image splicing forgery. The research on image forgery detection using CNN, a deep learning network, and research on detecting and localizing forgery in pixel units are in progress. Among them, CAT-Net, which learns the discrete cosine transform coefficients of images together with images, was released in 2022. The DCT coefficients presented by CAT-Net are combined with the JPEG artifact learning module and the backbone model as pre-learning, and the weights are fixed. The dataset used for pre-training is not included in the public dataset, and the backbone model has a relatively large number of network parameters, which causes overfitting in a small dataset, hindering generalization performance. In this paper, this learning module is designed to learn the characterization depending on the DCT domain in real-time during network training without pre-training. The DCT RRU-Net proposed in this paper is a network that combines RRU-Net which detects forgery by learning only images and JPEG artifact learning module. It is confirmed that the network parameters are less than those of CAT-Net, the detection performance of forgery is better than that of RRU-Net, and the generalization performance for various datasets improves through the network architecture and training method of DCT RRU-Net.

• The Journal of Pediatrics of Korean Medicine
• /
• v.22 no.1
• /
• pp.13-24
• /
• 2008

Objectives This study was designed to analyze the clinical studies on Mental retardation(MR) in traditional Chinese medicine(TCM). Methods For this study, we searched the clinical studies on MR, which had been published from 2003 to 2007, through web site CNKI(中國知識基礎設施工 http://www.cnki.net). There were 17 clinical studies and we focused on those studies. Results 1. In those Chinese studies, they used following words to describe Mental retardation; 小人弱智($xi\check{a}o\acute{e}rru\grave{o}zh\grave{i}$), 智能發育不全($zh\grave{i}n\acute{e}ngf\bar{a}y\grave{u}buqu\acute{a}n$), 智力低下($zh\grave{i}l\grave{i}d\bar{i}xi\grave{a}$), 精神發育遲滯($j\bar{i}ngsh\acute{e}f\bar{a}y\grave{u}ch\acute{i}zh\grave{i}$), 智能落后($zh\grave{i}n\acute{e}nglu\grave{o}h\grave{o}u$), 智能落后($zh\grave{i}n\acute{e}ngch\acute{i}hu\check{a}n$), 失天愚型患人($xi\bar{a}nti\bar{a}ny\acute{u}x\acute{i}nghu\grave{a}n'\acute{e}r$). 2. There were many kinds of TCM treatment methods for MR, such as herbal medicine, acupuncture, electroacupunture, acupoint injection, Chuna therapy, and special education. And those TCM treatments methods showed higher efficacies in the treatment of MR compared with Western medicine. 3. Mental retardation was related with the deficiency of heart, kidney, liver, spleen(心虛, 腎虛, 肝虛, 脾虛) and the pathological mechanism of Phlegm(絹) and Blood stasis(慫沂)in the studies about the Bian Zheng-the types of differential diagnosis- of MR. 4. Most of studies used Intelligence Quotient(IQ) to assess the efficacy of TCM treatment of MR. And the duration of treatment, the degree of illness, the age of patient, and the cause of illness affected the prognosis of MR. Conclusions These results suggest that traditional medicine could be one of the useful treatments on MR. And these results could be used in the clinical practices and studies on MR in Korea.