• International Journal of Computer Science & Network Security
• /
• 제21권7호
• /
• pp.182-190
• /
• 2021

Deep learning is an advanced technology for large-scale data analysis, with numerous promising cases like image processing, object detection and significantly more. It becomes customarily to use transfer learning and fine-tune a pre-trained CNN model for most image recognition tasks. Having people taking photos and tag themselves provides a valuable resource of in-data. However, these tags and labels might be noisy as people who annotate these images might not be experts. This paper aims to explore the impact of noisy labels on fine-tuning pre-trained CNN models. Such effect is measured on a food recognition task using Food101 as a benchmark. Four pre-trained CNN models are included in this study: InceptionV3, VGG19, MobileNetV2 and DenseNet121. Symmetric label noise will be added with different ratios. In all cases, models based on DenseNet121 outperformed the other models. When noisy labels were introduced to the data, the performance of all models degraded almost linearly with the amount of added noise.

• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.583-599
• /
• 2022

Although the object detection accuracy with a single image has been significantly improved with the advance of deep learning techniques, the detection accuracy for pig monitoring is challenged by occlusion problems due to a complex structure of a pig room such as food facility. These detection difficulties with a single image can be mitigated by using a video data. In this research, we propose a method in pig detection for video monitoring environment with a static camera. That is, by using both image processing and deep learning techniques, we can recognize a complex structure of a pig room and this information of the pig room can be utilized for improving the detection accuracy of pigs in the monitored pig room. Furthermore, we reduce the execution time overhead by applying a pruning technique for real-time video monitoring on an embedded board. Based on the experiment results with a video data set obtained from a commercial pig farm, we confirmed that the pigs could be detected more accurately in real-time, even on an embedded board.

• Nutrition Research and Practice
• /
• 제13권6호
• /
• pp.521-528
• /
• 2019

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. MATERIALS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of $150{\times}150$ and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

• Journal of Biosystems Engineering
• /
• 제38권3호
• /
• pp.199-207
• /
• 2013

Purpose: Tomatoes, an important agricultural product in fresh-cut markets, are sometimes a source of foodborne illness, mainly Salmonella spp. Growth cracks on tomatoes can be a pathway for bacteria, so its detection prior to consumption is important for public health. In this study, multispectral Visible/Near-Infrared (NIR) reflectance imaging techniques were used to determine optimal wavebands for the classification of defect tomatoes. Methods: Hyperspectral reflectance images were collected from samples of naturally cracked tomatoes. To classify the resulting images, the selected wavelength bands were subjected to two-band permutations, and a supervised classification method was used. Results: The results showed that two optimal wavelengths, 713.8 nm and 718.6 nm, could be used to identify cracked spots on tomato surfaces with a correct classification rate of 91.1%. The result indicates that multispectral reflectance imaging with optimized wavebands from hyperspectral images is an effective technique for the classification of defective tomatoes. Conclusions: Although it can be susceptible to specular interference, the multispectral reflectance imaging is an appropriate method for commercial applications because it is faster and much less expensive than Near-Infrared or fluorescence imaging techniques.

• Journal of Biosystems Engineering
• /
• 제39권3호
• /
• pp.166-173
• /
• 2014

Purpose: In this study, we focused on the image processing method to determine the external quality of Fuji apples by identifying surface defects such as scabs and bruises. Method: A CCD camera was used to capture filter images with 24 different wavelengths ranging between 530 nm and 1050 nm. Image subtraction and division operations were performed to distinguish the defect area from the normal areas including calyx, stem, and glaring on the apple surface image. All threshold values of the image were examined to reveal the defect area of pretreated filter images. Results: The developed operation methods were [image (720 nm) - image (900 nm)]/image (700 nm) for bruise detection and [image (740 nm) - image (900 nm)]/image (590 nm) for scab detection, which revealed 81% and 90% recognition ratios, respectively. Conclusions: Our results showed several optimal wavelengths and image processing methods to detect Fuji apple surface defects such as bruises and scabs.

• 한국가시화정보학회지
• /
• 제22권2호
• /
• pp.27-34
• /
• 2024

In this study, we propose a novel approach for rapid and accurate pathogen detection by integrating Polydiacetylene (PDA) hydrogel sensors with advanced deep learning algorithms and visualization techniques. PDA hydrogel sensors exhibit a color transition in the presence of pathogens, enabling straightforward and quick pathogen detection. We developed a reliable pathogen detection system that combines deep neural network algorithms with color quantification technology for image-based analysis. This image-based system retains the ease of pathogen detection offered by PDA sensors while deriving quantified color standards to overcome the limitations of human visual assessment, enhancing reliability. This advancement contributes to public health and the development and application of pathogen detection technology.

• Journal of Multimedia Information System
• /
• 제7권1호
• /
• pp.17-24
• /
• 2020

Rice (Oryza Sativa) is an important source of food for the people of our country, even though of world also .It is also considered as the staple food of our country and we know agriculture is the main source country's economy, hence the crop of Rice plays a vital role over it. For increasing the growth and production of rice crop, ground-breaking technique for the detection of any type of disease occurring in rice can be detected and categorization of rice crop diseases has been proposed in this paper. In this research paper, we perform comparison between two classifiers namely MDC and Bayes' classifiers Survey over different digital image processing techniques has been done for the detection of disease in rice crops. The proposed technique involves the samples of 200 digital images of diseased rice leaf images of five different types of rice crop diseases. The overall accuracy that we achieved by using Bayes' Classifiers and MDC are 69.358 percent and 81.06 percent respectively.

• Journal of Biosystems Engineering
• /
• 제39권2호
• /
• pp.142-149
• /
• 2014

Purpose: A multispectral algorithm for detection and differentiation of defective (defects on apple skin) and normal Red Delicious apples was developed from analysis of a series of hyperspectral line-scan images. Methods: A fast line-scan hyperspectral imaging system mounted on a conventional apple sorting machine was used to capture hyperspectral images of apples moving approximately 4 apples per second on a conveyor belt. The detection algorithm included an apple segmentation method and a threshold function, and was developed using three wavebands at 676 nm, 714 nm and 779 nm. The algorithm was executed on line-by-line image analysis, simulating online real-time line-scan imaging inspection during fruit processing. Results: The rapid multispectral algorithm detected over 95% of defective apples and 91% of normal apples investigated. Conclusions: The multispectral defect detection algorithm can potentially be used in commercial apple processing lines.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.334-343
• /
• 1996

Quality evaluation for food and agricultural products have always been one of the most elusive problems associated with the handling , processing and marketing in a food plant production. In order to detect physical foreign materials in food and agricultural products, non-destructive techniques have been developed for many years. Application of X-ray system to detect physical foreign materials in food and agricultural products could be considered to be a high potential method. Especially , it is impossible to detect internal physical foreign materials by visual inspections. In this study, it was tried to be applied for two different X-ray devices. Soft X-ray system with CdTe sensor and X-ray CT scanner were evaluated for advantage of the detection of non-meltallic foreign materials in food and agricultural products . Though the soft X-ray is not a high energy radiation, it is possible to detect small different density in a material. The CdTe sensor has a high resolution for t e soft X-ray energy region. The density characteristics of foods and foreign material were expressed region. The density characteristics of foods and foreign materials were expressed as a soft X-ray energy spectrum. The energy spectrum was analyzed by a personal computer with a multi-channel analyzer. X-ray CT scanner can provide visual image and analyze by three dimensional information inside food and agricultural products. The X-ray CT scanner using as a medical equipment was used to detect a foreign material. The density characteristics of food and foreign materials in food were tried to be detected by the threshold value on the basis of the CT numbers. The soft X-ray absorption characteristics for acrylin plates and distilled water were obtained and could be found the possibility of detecting a small physical foreign materials such as a plastic wrapping film , a stone and grasshopper in food and agricultural products.

• 한국정보통신학회논문지
• /
• 제21권10호
• /
• pp.1950-1956
• /
• 2017

정밀 푸드 프린팅 분야에서 출력 대상물의 정밀한 측위기술은 대단히 중요하다. 본 논문에서는 영상처리를 통하여 라떼 아트 프린터의 커피 잔을 정밀하게 측위하는 방법을 제안한다. 프린터 상단 측면에 설치된 카메라 센서로부터 얻은 이미지를 투영변환을 통하여 Top-View 이미지로 변환하고 이미지의 에지를 검출 후 Circular Hough 변환을 통하여 컵의 중심점 및 반지름을 검출하였다. 성능 평가 결과 0.1 ~ 0.125초의 영상 처리 속도, 92.26% 의 컵 검출률을 보여 라떼 아트 출력 소요 시간에 영향을 거의 주지 않으면서 거의 완벽하게 컵을 검출하는 것을 확인하였으며, 검출된 컵의 중심점 좌표 및 반지름 값들이 평균적으로 1.5mm 이내의 매우 적은 오차를 보여 본 논문이 해결하고자 했던 인쇄 위치 오차 문제를 해결한 것으로 평가된다.