Development of a well-structured industrial vision system

Bien, Zeungnam; Oh, S.-R.; Won, Jonghwa; You, Bum-Jae; Han, Dongil; Kim, J.O.

doi:10.1109/iecon.1990.149191

Cited by 9 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, finding a universal set of image preprocessing steps for actual PCB components and markings that have various colors is a nontrivial problem. A conventional way to locate the positions of component markings is by calculating the project profile of the component image which is converted to binary or grayscale [29]. In [30], the region that only contains the component markings is specified in the inspection system.…”

Section: B Text Spotting Modelsmentioning

confidence: 99%

“…For character-level text recognition, image processing techniques such as projection profile [29], counting the column-sum of text (e.g., white) pixels [30], and text contour border detection adopted from Suzuki's border-following algorithm [31] are used to segment PCB component text markings into individual characters before the character recognition stage. Yet, these methods are ineffective in segmenting a character that is not well-connected or multiple characters that are close to one another.…”

Section: B Text Spotting Modelsmentioning

confidence: 99%

“…Also, in [17] and [18], programmed inspection software may segment printed characters on PCB components but manual corrections are often needed, especially for fonts that have short distances in between characters. After getting the segmented character images, a straightforward character recognition method is by matching each of them with the stored patterns and checking for the degree of mismatch according to a selected threshold [29]. Another way is to apply feature extraction methods like projection profile, zoning, moments, and contour profile on the segmented characters to classify them into different character classes [30].…”

Section: B Text Spotting Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Synthetic Data Generation for Text Spotting on Printed Circuit Board Component Images

Liau,

Chi Tay,

Mohamed

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Machine vision systems with programmed text detection and text recognition features are useful in manufacturing process to automatically locate and read text markings on mounted printed circuit board (PCB) components. To better handle input images with varying image quality, text quality, and text variations, the robustness of deep learning approach for end-to-end text spotting on PCB component images is worth exploring. However, limitations of public PCB component datasets for such research and imbalance of data in actual collected PCB component datasets hinder the training of deep learning text spotting model, and consequently necessitate the generation of synthetic data. In this study, a synthetic PCB component dataset is generated using our synthetic data generator that adds synthetic text with random character sequences on manually edited PCB component images to elevate the realism of the synthetic images. The synthetic dataset covers 66 character classes while providing synthetic text with diverse text variations in font, style, size, and color. We train an existing text spotting model called Text Perceptron using both real and synthetic datasets to detect and recognize arbitrary-shaped text markings on PCB components. Our synthetic PCB component dataset has improved the text spotting performance of Text Perceptron. The trained model achieves promising text detection result and encouraging end-to-end text spotting F-score on real PCB component images. It also meets an acceptable average inference time per image. Still, the text spotting performance of the trained model needs improvement to realize deployment for PCB component inspection.

show abstract

Section: B Text Spotting Modelsmentioning

confidence: 99%

Section: B Text Spotting Modelsmentioning

confidence: 99%

Section: B Text Spotting Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Synthetic Data Generation for Text Spotting on Printed Circuit Board Component Images

Liau,

Chi Tay,

Mohamed

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The VISIONbus, used IC inspection vision machine [13], connects heterogeneous modules together. Operating at 6.3 MHz, this bus allows 256 ϫ 256 image transfers at the frame rate.…”

Section: Industrial Data Path Machinesmentioning

confidence: 99%

An Open Bus Architecture for Real-Time Video Applications

Al-Awa¹,

Coulon²,

Fristot³

et al. 1998

Real-Time Imaging

View full text Add to dashboard Cite

“…Computer vision systems are designed for automatic recognition, determination of the coordinates, visual inspection of free-form objects and are used in different branches of science and technology. Contribution to the development of methods and computer vision identification systems was made by Haushtayn H.D., Khlytchiev M.S., Sadykov S.S., Titov V.S., Syryamkin V.I., S. Draghici, О. Martinsky, H. Kwasnicka, S. Sexton, J. Wentworth [1,2,3].…”

Section: Introductionmentioning

confidence: 99%