• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.11
• /
• pp.63-68
• /
• 2019

The dimensional quality of flexible foams is often difficult to be evaluated through general machine vision inspection methods due to the free deformation of the outer shape. For the evaluation of the dimensions of flexible foams, methods of estimating the size of the product through the expansion rate of the product surface are evaluated. Specimens with various dimensions and surface gratings are prepared, and the degree of surface expansion is measured through machine vision. The correlation, between the measured surface grid size and the actual size of test specimens, is analyzed. We further analyze the correlation between the size of test specimens and the position of the surface grid. This study provides a basis for estimating the actual dimensions of specimens by measuring the surface expansion of flexible foams.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.689-699
• /
• 2016

As the demand for LCD increases, the importance of inspection equipment for improving the efficiency of LCD production is continuously emphasized. The pattern inspection apparatus is one that detects minute defects of pattern quickly using optical equipment such as line scan camera. This pattern inspection apparatus makes a decision on whether a pixel is a defect or not using a single threshold value in order to meet constraint of real time inspection. However, a method that uses an adaptive thresholding scheme with different threshold values according to characteristics of each region in a pattern can greatly improve the performance of defect detection. To apply this adaptive thresholding scheme it has to be known that a certain pixel to be inspected belongs to which region. Therefore, this paper proposes a region matching algorithm that recognizes the region of each pixel to be inspected. The proposed algorithm is based on the pattern matching scheme with the consideration of real time constraint of machine vision and implemented through GPGPU in order to be applied to a practical system. Simulation results show that the proposed method not only satisfies the requirement for processing time of practical system but also improves the performance of defect detection.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.245-254
• /
• 2002

IC package marking inspection system using machine vision locates and identifies the target elements from input image, and decides the quality of marking by comparing the extracted target elements with the standard patterns. This paper proposes an adaptive multi-level thresholding (AMLT) method which is suitable for a series of operations such as locating the target IC package, extracting the characters, and detecting the Pinl dimple. It also proposes a dynamic matching unit selection (DMUS) method which is robust to noises as well as effective to catch out the local marking errors. The main idea of the AMLT method is to restrict the inputs of Otsu's thresholding algorithm within a specified area and a partial range of gray values. Doing so, it can adapt to the specific domain. The DMUS method dynamically selects the matching unit according to the result of character extraction and layout analysis. Therefore, in spite of the various erroneous situation occurred in the process of character extraction and layout analysis, it can select minimal matching unit in any environment. In an experiment with 280 IC package images of eight types, the correct extracting rate of IC package and Pinl dimple was 100% and the correct decision rate of marking quality was 98.8%. This result shows that the proposed methods are effective to IC package marking inspection.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.10 s.241
• /
• pp.1416-1429
• /
• 2005

In order to meet the increasing competitive pressures coupled with higher demands for component quality, whirling machines have been at the cutting edge of the automobile industry for more than 25 years. The hard whirling process can save on machining time and operation elimination. Hard whirling is done dry, without coolant. The chips carry away nearly all of the heat during cutting, leaving the workpiece cool and minimizing any thermal geometry variations. The surface finish and profile accuracy are close to grinding quality. Whirling machines usually consist of four major parts; 1) loading system that requires the necessary axial speeds, 2) head stock that needs high precision clamping and positioning system at the chuck and tailstock, 3) whirling unit that demands the high cutting speeds and cutting power fer cutting deep thread profiles and 4) unloading system that requires an easy workpiece unloading. Also, capabilities of the whirling machine can be improved by attaching a vision system to the machine. Most of whirling machines in Korean automobile industry are imported from the Leistritz company, Germany and the Hasegawa company, Japan. Tn this paper, a basic research will be performed to improve and enhance the existing whirling machines. Finally, a new Korean whirling machine will be proposed and developed.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.