Search Results

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
Manufacturing Process Improvement by Barcode Reader using Image Processing
(2024-01-01)
Sukasem, Sutikamon
;
Maneerat, Noppadol
;
Thudthong, Jakkrit
;
Wongsomboon, Chanathip
;
Yajima, Kuniaki
Manufacturing industries get perspective on the efficiency of their production process. This study focuses on improving the cycle time of the work process at the station related to barcode reading. This operation should be of minimal duration to result in shorter cycle times and resulting in increased production volumes while still maintaining quality and reducing production costs. Image processing methodology is applied to reading barcodes instead of using a barcode reader which creates clear image quality along with developing an application using Android Bridge (ABD) and ZXing libraries that can read 1D barcodes in many formats. More essentially, application development by multithreading programming can process barcode reading simultaneously at a time that meets the target cycle time. The result of this study proves that the process of reading barcodes by human work has taken 60 times per job cycle and the reading time was about 29 seconds, becoming reduced to 19.85 seconds, manpower can be reduced by 1 person and production cost as well. Moreover, this implementation eliminates human errors that are likely to occur from scanning barcodes in the wrong position. Therefore, this study has benefited the manufacturing industry achieve significantly increased productivity and efficiency.
Some of the metrics are blocked by your
consent settings
Detection of cotton wool for diabetic retinopathy analysis using neural network
(2017-12-13)
Bui, Toan
;
Maneerat, Noppadol
;
Watchareeruetai, Ukrit
This paper presents an automatic segmentation method used to detect cotton wool spots in the retinal images for diabetic retinopathy disease. An early detection of cotton wool is important to prevent the dangerous damage which may cause blindness and vision loss. A preprocessing is applied to enhance image quality followed by optic disc removal. A feature extraction method is used to take useful elements from the image for increasing accuracy in classification step. A neural network model is employed for learning task and tested by k-fold cross validation. Our approach is evaluated by ground truth on DIARETDB1 public data. The result shows that cotton wool can be segmented by this method with 85.9% in sensitivity, 84.4% in specificity, and 85.54% in accuracy.
Some of the metrics are blocked by your
consent settings
A design of colorimeter for chemical quantitative analysis based on a web-camera
(2017-10-19)
Phongern, Komsun
;
Mathaweesansurn, Arjnarong
;
Maneerat, Noppadol
;
Chengchan, Nathawut
This paper presents the design of colorimeter for chemical quantitative analysis based on image processing. It comprises of two main parts which are test box and software. The test box consists of a web camera and LED lamp plat which is used to illuminate a micro wells. The software is graphic user interface and image processing. The main of image processing are split RGB channel of each pit in micro wells so calculate calibration curves for finding and unknown concentric solution then show result on screen. The experiment shows the design in this paper can calculate concentric of the solution. The result of the experiment have a correlation of reaction between Fe (II) and Phenanthroline (Red product) 0.985, the reaction between Ethanol and Methyl orange (Yellow product) 0.933 and reaction between Uric acid and Phosphotungstic acid (Blue product) 0.986. Moreover it takes a less time and lower cast compared with the spectrophotometer. The device can be applied to chemical laboratory by possibility.
Some of the metrics are blocked by your
consent settings
A mobile phone-based analyzer for quantitative determination of urinary albumin using self-calibration approach
(2017-04-01)
Mathaweesansurn, Arjnarong
;
Maneerat, Noppadol
;
Choengchan, Nathawut
This work demonstrates use of a smart mobile phone installed with an Android application, termed ‘Albumin smart test’, as an analyzer for quantitative determination of urinary albumin. The reaction between albumin and tetrabromophenolphthalein ethyl ester (TBPE) in the presence of Triton X-100 was employed for detection principle.The mobile phone was exploited with the sample cassette and the test paper. One sample cassette composes of two holders for accommodation of control and test samples. The test paper was designed in order to contain standard colorimetric strip and space for situating the sample cassette. Optical images of the strip and the samples were simultaneously captured in a single shot by a digital camera of the mobile phone and were digitally processed by the developed application for quantification of the albumin concentration based on self-calibration approach. With the advantage of self-calibration, the albumin test by our mobile phone can be performed in ambient light without using any extra module integrated with lighting control device. The other advantages are portability, ease of implementation and rapid analysis (3 min) with high precision (RSD ≤ 2.5%) and high accuracy (Recovery = 98.7% ± 1.6). The mobile device was successfully applied to diagnosis of microalbuminuria.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results