The requirement of product quality inspection in industries for product standardized leads to a development of the quality inspection system. The problem is related to a manual inspection that is done by a human as an inspector. This paper presents an automated real-time vision quality inspection monitoring system as a problem solver to a manual inspection that is tedious and time-consuming task as well as reducing cost especially in small and medium enterprise industries (SME). For the proposed system, soft drink is used as the test product for quality inspection. The system uses computer-network to inspect two quality inspections which are color concentration and water level. The analysis includes pre-processing, color concentration using the histogram and quadratic distance and level inspection using coordinate vertical and horizontal reference levels. The similarities of both experimental and simulation results are obtained for both parameters which are 100% accuracy using 205 samples.
Difussion-Weighted Imaging (DWI) plays an important role in the diagnosis of brain stroke by providing detailed information regarding the soft tissue contrast in the brain organ. Conventionally, the differential diagnosis of brain stroke lesions is performed manually by professional neuroradiologists during a highly subjective and time- consuming process. This study proposes a segmentation and classification technique to detect brain stroke lesions based on diffusion-weighted imaging (DWI). The type of stroke lesions consists of acute ischemic, sub-acute ischemic, chronic ischemic and acute hemorrhage. For segmentation, fuzzy c-Means (FCM) and active contour is proposed to segment the lesion’s region. FCM is implemented with active contour to separate the cerebral spinal fluid (CSF) with the hypointense lesion. Pre-processing is applied to the DWI for image normalization, background removal and image enhancement. The algorithm performance has been evaluated using Jaccard Index, Dice Coefficient (DC) and both false positive rate (FPR) and false negative rate (FNR). The average results for the Jaccard index, DC, FPR and FNR are 0.55, 0.68, 0.23 and 0.23, respectively. First statistical order method is applied to the segmentation result to obtain the features for the classifier input. For classification technique, bagged tree classifier is proposed to classify the type of stroke. The accuracy results for the classification is 90.8%. Based on the results, the proposed technique has potential to segment and classify brain stroke lesion from DWI images.
<span>This paper proposed a new analysis technique of brain tumor segmentation and classification for Fluid Attenuated Inversion Recovery (FLAIR) Magnetic Resonance Images (MRI). 25 FLAIR MRI images were collected from online database of Multimodal Brain Tumor Segmentation Challenge 2015 (BRaTS’15). The analysis comprised four stages which are preprocessing, segmentation, feature extraction and classification. Fuzzy C-Means (FCM) was proposed for brain tumor segmentation. Mean, median, mode, standard deviation, area and perimeter were calculated and utilized as the features to be fed into a rule-based classifier. The segmentation performances were assessed based on Jaccard, Dice, False Positive and False Negative Rates (FPR and FNR). The results indicate that FCM offered high similarity indices which were 0.74 and 0.83 for Jaccard and Dice indices, respectively. The technique can possibly provide high accuracy and has the potential to detect and classify brain tumor from FLAIR MRI database.</span>
Stroke is a “brain attack” that often causes paralysis, resulted from either bleeding in the brain (hemorrhagic) or the blockage of blood flow to the brain (ischemic). It posed a big challenge to Malaysian healthcare services with at least 32 deaths per day, while survivors were burdened with multiple problems. Conventionally, the diagnosis is performed manually by neuroradiologists during a highly subjective and time consuming tasks. Therefore, this paper intends to diagnose and classify stroke by investigating diffusion- weighted imaging (DWI) of brain stroke images using Bagged Tree classification. Stroke is classified into three main types which are acute stroke, chronic stroke and hemorrhage stroke. The performance of the proposed method is then verified using accuracy and Area Under the Curve (AUC). Based on the results, the overall accuracy for the classification is 96.7%. The AUC of each type of stroke for acute stroke, chronic stroke and hemorrhage stroke is 97%, 100% and 99%, respectively. This outcome could serve as an insight to improve the healthcare of the community by providing better solutions using such intelligent system.
<p> In recent years, the utilization of digital instruments in industries is quickly expanding. This is because digital instruments are typically more exact than the analog instruments, and easier to be read as they are hooked up to a liquid-crystal display (LCD). However, manual data entry from LCD display is tedious and less accurate. This paper proposes a real-time LCD digit recognition system for the industrial purposes. The system is interfaced with an IP webcam to capture the video frames from the LCD display. The digital data is pre-processed into grayscale and being cropped into a selected region of interest (ROI). Adaptive thresholding and morphological operation are applied for the digit segmentation process. Data extraction and characterization are done by utilizing neural network classifier. Finally, all the information are logged out to Microsoft Excel spreadsheet. The 90% accuracy is accomplished for 50 test images of various LCD display.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.