• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.9
• /
• pp.858-862
• /
• 2015

This paper presents a new forward-viewing mono-camera based obstacle detection algorithm for mobile robots. The proposed method extracts the coarse location of an obstacle in an image using inverse perspective mapping technique from sequential images. In the next step, graph-cut based image labeling is conducted for estimating the exact obstacle boundary. The graph-cut based labeling algorithm labels the image pixels as either obstacle or floor as the final outcome. Experiments are performed to verify the obstacle detection performance of the developed algorithm in several examples, including a book, box, towel, and flower pot. The low illumination condition, low color contrast between floor and obstacle, and floor pattern cases are also tested.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.386-398
• /
• 2020

We developed an integrative annotation program that can perform data labeling process for deep learning models in object recognition. The program utilizes the basic GUI library of Python and configures crawler functions that allow data collection in real time. Retinanet was used to implement an automatic annotation function. In addition, different data labeling formats for Pascal-VOC, YOLO and Retinanet were generated. Through the experiment of the proposed method, a domestic vehicle image dataset was built, and it is applied to Retinanet and YOLO as the training and test set. The proposed system classified the vehicle model with the accuracy of about 94%.

• Asian-Australasian Journal of Animal Sciences
• /
• v.19 no.8
• /
• pp.1106-1110
• /
• 2006

In the meat industry, correct breed information in food labeling is required to assure meat quality. Genetic markers provide corroborating evidence to identify breed. This paper describes the development of DNA markers to discriminate between Japanese Black and F1 (Japanese Black${\times}$Holstein) breeds. The amplified fragment length polymorphism method was employed to detect candidate markers absent in Japanese Black but present in Holstein. The 1,754 primer combinations yielded eleven markers that were converted into single nucleotide polymorphism markers for high-throughput genotyping. The allele frequencies in both breeds were investigated for discrimination ability using PCR-RFLP. The probability of identifying F1 was 0.9168 and probability of misjudgment was 0.0066 using four selected markers. The markers could be useful for discriminating between Japanese Black and F1 and would contribute to the prevention of falsified breed labeling of meat.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.78-81
• /
• 2012

In this paper, we proposed the new vehicle license plates detection method which is available in a various fields, including vehicle access control, illegal parking and speeding vehicle crack down. First, we binarize an image by using difference of gaussian filter to find a sequence of numbers of plates. Second, we determine the plate region by labeling repeatedly using the morphological characteristics of the plates. Finally, we use a projective transformation for correcting the distortion that occurs because of the camera or the location of the vehicle.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.5
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• Journal of Food Hygiene and Safety
• /
• v.27 no.4
• /
• pp.325-331
• /
• 2012

Food allergy refers to an immunologically mediated adverse reaction to food, mainly to proteinaceous constituents. Health implications vary between those individuals who experience mild physical discomforts to those with fast-acting, life-threatening anaphylactic reactions. The prevalence of food allergy is higher in children than in adults, estimated around 4-8% and 1-2% respectively in developed countries. Food allergy has no effective cure at the present time and total avoidance of causative foods is the most reliable prophylactic method currently recommended by the medical community. To help food allergic patients to make informed choices of their foods, mandatory labeling of selected food allergens has been introduced in several countries. All food allergen labelling provisions specify a set of allergens common to the regulated countries. Policy divergence, however, exists between countries by inclusion of additional allergens unique to specific countries and enforcement of specific labelling requirements. Such variations in food allergen labelling regulations make it difficult to manage allergen labeling in imported pre-packaged food products. This paper addresses two current issues in food allergen regulation: 1) an urgent need to determine true prevalence of food allergy in the Asia-Pacific region. This will enable refinement to the food allergen regulation to be more country-specific rather than simply adopting CODEX recommendations. 2) There is an urgent need for harmonization of food allergen regulation in order to prevent food allergen regulation becoming a trade barrier.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.74-79
• /
• 2019

Traditional compound noun decomposition algorithms often face challenges of decomposing compound nouns into separated nouns when unregistered unit noun is included. It is very difficult for those traditional approach to handle such issues because it is impossible to register all existing unit nouns into the dictionary such as proper nouns, coined words, and foreign words in advance. In this paper, in order to solve this problem, compound noun decomposition problem is defined as tag sequence labeling problem and compound noun decomposition method to use syllable unit embedding and deep learning technique is proposed. To recognize unregistered unit nouns without constructing unit noun dictionary, compound nouns are decomposed into unit nouns by using LSTM and linear-chain CRF expressing each syllable that constitutes a compound noun in the continuous vector space.

• Korean Journal of Organic Agriculture
• /
• v.30 no.3
• /
• pp.335-350
• /
• 2022

The purpose of this study is to help operate and manage the new food period system by investigating consumer perception of sell-by-date and use-by-date, and change of purchasing and consumption period by food period label. Although they have opinions that fit the purpose of introducing the system, such as the need to introduce a use by date, extending the food intake period, and reducing food waste, they still lack an accurate understanding of the system, so education or publicity is needed. In addition, no matter what form of use by date is introduced, products with food expiration date are still likely to be returned or discarded. Therefore, it is desirable to adjust the setting criteria or safety factor for each deadline rather than changing the food period labeling method. In order to reduce consumer confusion and food waste, it is judged that the parallel marking of the sell by date and use by date is appropriate.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• Nuclear Engineering and Technology
• /
• v.55 no.11
• /
• pp.4057-4065
• /
• 2023

Organic scintillators are widely used for neutron/gamma detection. Pulse shape discrimination algorithms have been commonly used to discriminate the detected radiations. These algorithms have several limits, in particular with plastic scintillator which has lower discrimination ability, compared to liquid scintillator. Recently, machine learning (ML) models have been explored to enhance discrimination performance. Nevertheless, obtaining an accurate ML model or evaluating any discrimination approach requires a reference neutron dataset. The preparation of this is challenging because neutron sources are also gamma-ray emitters. Therefore, this paper proposes a pipeline to prepare clean labeled neutron/gamma datasets acquired by an organic scintillator. The method is mainly based on a Time of Flight setup and Tail-to-Total integral ratio (TTT_ratio) discrimination algorithm. In the presented case, EJ276 plastic scintillator and ²⁵²Cf source were used to implement the acquisition chain. The results showed that this process can identify and remove mislabeled samples in the entire ToF spectrum, including those that contribute to peak values. Furthermore, the process cleans ToF dataset from pile-up events, which can significantly impact experimental results and the conclusions extracted from them.