• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3708-3728
• /
• 2021

Indian herbal plants are used in agriculture and in the food, cosmetics, and pharmaceutical industries. Laboratory-based tests are routinely used to identify and classify similar herb species by analyzing their internal cell structures. In this paper, we have applied computer vision techniques to do the same. The original leaf image was preprocessed using the Chan-Vese active contour segmentation algorithm to efface the background from the image by setting the contraction bias as (v) -1 and smoothing factor (µ) as 0.5, and bringing the initial contour close to the image boundary. Thereafter the segmented grayscale image was fed to a leaky capacitance fired neuron model (LCFN), which differentiates between similar herbs by combining different groups of pixels in the leaf image. The LFCN's decay constant (f), decay constant (g) and threshold (h) parameters were empirically assigned as 0.7, 0.6 and h=18 to generate the 1D feature vector. The LCFN time sequence identified the internal leaf structure at different iterations. Our proposed framework was tested against newly collected herbal species of natural images, geometrically variant images in terms of size, orientation and position. The 1D sequence and shape features of aloe, betel, Indian borage, bittergourd, grape, insulin herb, guava, mango, nilavembu, nithiyakalyani, sweet basil and pomegranate were fed into the 5-fold Bayesian regularization neural network (BRNN), K-nearest neighbors (KNN), support vector machine (SVM), and ensemble classifier to obtain the highest classification accuracy of 91.19%.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.107-116
• /
• 2022

Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment of human-inaccessible facilities. This research was conducted to study the conditions of deep learning-based imaging data on bridges and to develop an evaluation prototype program for bridges. To develop a deep learning-based bridge damage detection prototype, the Semantic Segmentation model, which enables damage detection and quantification among deep learning models, applied Mask-RCNN and constructed learning data 5,140 (including open-data) and labeling suitable for damage types. As a result of performance modeling verification, precision and reproduction rate analysis of concrete cracks, stripping/slapping, rebar exposure and paint stripping showed that the precision was 95.2 %, and the recall was 93.8 %. A 2^nd performance verification was performed on onsite data of crack concrete using damage rate of bridge members.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.434-440
• /
• 2022

Liver transplantation is a critical used treatment method for patients with end-stage liver disease. The number of cases of living donor liver transplantation is increasing due to the imbalance in needs and supplies for brain-dead organ donation. As a result, the importance of the accuracy of the donor's suitability evaluation is also increasing rapidly. To measure the donor's liver volume accurately is the most important, that is absolutely necessary for the recipient's postoperative progress and the donor's safety. Therefore, we propose liver segmentation in abdominal CT images from pre-operation, POD 7, and POD 63 with a two-dimensional U-Net. In addition, we introduce an algorithm to measure the volume of the segmented liver and measure the hepatectomy rate and regeneration rate of pre-operation, POD 7, and POD 63. The performance for the learning model shows the best results in the images from pre-operation. Each dataset from pre-operation, POD 7, and POD 63 has the DSC of 94.55 ± 9.24%, 88.40 ± 18.01%, and 90.64 ± 14.35%. The mean of the measured liver volumes by trained model are 1423.44 ± 270.17 ml in pre-operation, 842.99 ± 190.95 ml in POD 7, and 1048.32 ± 201.02 ml in POD 63. The donor's hepatectomy rate is an average of 39.68 ± 13.06%, and the regeneration rate in POD 63 is an average of 14.78 ± 14.07%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.958-979
• /
• 2023

Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1807-1822
• /
• 2023

Innovation and rapid increased functionality in user friendly smartphones has encouraged shutterbugs to have picturesque image macros while in work environment or during travel. Formal signboards are placed with marketing objectives and are enriched with text for attracting people. Extracting and recognition of the text from natural images is an emerging research issue and needs consideration. When compared to conventional optical character recognition (OCR), the complex background, implicit noise, lighting, and orientation of these scenic text photos make this problem more difficult. Arabic language text scene extraction and recognition adds a number of complications and difficulties. The method described in this paper uses a two-phase methodology to extract Arabic text and word boundaries awareness from scenic images with varying text orientations. The first stage uses a convolution autoencoder, and the second uses Arabic Character Segmentation (ACS), which is followed by traditional two-layer neural networks for recognition. This study presents the way that how can an Arabic training and synthetic dataset be created for exemplify the superimposed text in different scene images. For this purpose a dataset of size 10K of cropped images has been created in the detection phase wherein Arabic text was found and 127k Arabic character dataset for the recognition phase. The phase-1 labels were generated from an Arabic corpus of quotes and sentences, which consists of 15kquotes and sentences. This study ensures that Arabic Word Awareness Region Detection (AWARD) approach with high flexibility in identifying complex Arabic text scene images, such as texts that are arbitrarily oriented, curved, or deformed, is used to detect these texts. Our research after experimentations shows that the system has a 91.8% word segmentation accuracy and a 94.2% character recognition accuracy. We believe in the future that the researchers will excel in the field of image processing while treating text images to improve or reduce noise by processing scene images in any language by enhancing the functionality of VGG-16 based model using Neural Networks.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.571-580
• /
• 2022

Marine deposited waste is a major cause of problems such as a lot of damage and an increase in the estimated amount of garbage due to abandoned fishing grounds caused by ghost fishing. In this paper, we implement a real-time marine deposited waste detection artificial intelligence system to understand the actual conditions of waste fishing gear usage, distribution, loss, and recovery, and study methods for performance improvement. The system was implemented using the yolov5 model, which is an excellent performance model for real-time object detection, and the 'data screening process' and 'class segmentation' method of learning data were applied as performance improvement methods. In conclusion, the object detection results of datasets that do screen unnecessary data or do not subdivide similar items according to characteristics and uses are better than the object recognition results of unscreened datasets and datasets in which classes are subdivided.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.465-467
• /
• 2022

Mobile phones have become an essential item nowadays since it provides access to online platform and service fast and easy. Coming to these platforms such as Social Network Service (SNS) for shopping have been a go-to option for many people. However, searching for a specific fashion item in the picture is challenging, where users need to try multiple searches by combining appropriate search keywords. To tackle this problem, we propose a system that could provide immediate access to websites related to fashion items. In the framework, we also propose a deep learning model for an automatic analysis of image contexts using instance segmentation. We use transfer learning by utilizing Deep fashion 2 to maximize our model accuracy. After segmenting all the fashion item objects in the image, the related search information is retrieved when the object is clicked. Furthermore, we successfully deploy our system so that it could be assessable using any web browser. We prove that deep learning could be a promising tool not only for scientific purpose but also applicable to commercial shopping.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.447-454
• /
• 2024

Construction site monitoring is pivotal for overseeing project progress to ensure that projects are completed as planned, within budget, and in compliance with applicable laws and safety standards. Additionally, it seeks to improve operational efficiency for better project execution. To achieve this, many researchers have utilized computer vision technologies to conduct automatic site monitoring and analyze the operational status of equipment. However, most existing studies estimate real-world 3D information (e.g., object tracking, work status analysis) based only on 2D pixel-based information of images. This approach presents a substantial challenge in the dynamic environments of construction sites, necessitating the manual recalibration of analytical rules and thresholds based on the specific placement and the field of view of cameras. To address these challenges, this study introduces a novel method for 3D visualization and status analysis of construction site objects using 3D reconstruction technology. This method enables the analysis of equipment's operational status by acquiring 3D spatial information of equipment from single-camera images, utilizing the Sam-Track model for object segmentation and the One-2-3-45 model for 3D reconstruction. The framework consists of three main processes: (i) single image-based 3D reconstruction, (ii) 3D visualization, and (iii) work status analysis. Experimental results from a construction site video demonstrated the method's feasibility and satisfactory performance, achieving high accuracy in status analysis for excavators (93.33%) and dump trucks (98.33%). This research provides a more consistent method for analyzing working status, making it suitable for practical field applications and offering new directions for research in vision-based 3D information analysis. Future studies will apply this method to longer videos and diverse construction sites, comparing its performance with existing 2D pixel-based methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.473-476
• /
• 2007

Location determination of mobile user via RSSI approach has received ample attention from researchers lately. However, it remains a challenging issue due to the complexities of RSSI signal propagation characteristics, which are easily exacerbated by the mobility of user. Hence, a segmentation-based linear spline interpolation method is proposed to cater for the dynamic fluctuation pattern of radio signal in complex environment. This optimization algorithm is proposed in addition to the current radiolocation's (CC2431, Chipcon, Norway) algorithm, which runs on IEEE802.15.4 standard. The enhancement algorithm involves four phases. First phase consists of calibration model in which RSSI values at different static locations are collected and processed to obtain the mean and standard deviation value for the predefined distance. RSSI smoothing algorithm is proposed to minimize the dynamic fluctuation of radio signal received from each reference node when the user is moving. Distances are computed using the segmentation formula obtain in the first phase. In situation where RSSI value falls in more than one segment, the ambiguity of distance is solved by probability approach. The distance probability distribution function(pdf) for each distances are computed and distance with the highest pdf at a particular RSSI is the estimated distance. Finally, with the distances obtained from each reference node, an iterative trilateration algorithm is used for position estimation. Experiment results obtained position the proposed algorithm as a viable alternative for location tracking.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.89-98
• /
• 2005

Fingerprint segmentation and ridge orientation estimation algorithms with images from a mobile camera are proposed. The fingerprint images from a mobile camera are quite different from those from conventional sensor, called touch based sensor such as optical, capacitive, and thermal. For example, the images from a mobile camera are colored and the backgrounds or non-finger regions are very erratic depending on how the image capture time and place. Also the contrast between ridge and valley of a mobile camera image are lower than that of touch based sensor image. To segment fingerprint region, we first detect the initial region using color information and texture information. The LUT (Look Up Table) is used to model the color distribution of fingerprint images using manually segmented images and frequency information is extracted to discriminate between in focused fingerprint regions and out of focused background regions. With the detected initial region, the region growing algerian is executed to segment final fingerprint region. In fingerprint orientation estimation, the problem of gradient based method is very sensitive to outlier that occurred by scar and camera noise. To solve this problem, we propose a robust regression method that removes the outlier iteratively and effectively. In the experiments, we evaluated the result of the proposed fingerprint segmentation algerian using 600 manually segmented images and compared the orientation algorithms in terms of recognition accuracy.