Parallel Algorithms to Detect and Classify Defects in Surface Steel Strips

Ahmed, Khaled R.; Al-Saeed, Majed; Al-Jumah, Maryam I.

doi:10.1007/978-3-030-70296-0_40

Cited by 2 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features include grayscale statistical features [ 44 ], local binary patterns (LBP) feature [ 45 ], histogram of oriented gradient (HOG) features [ 46 ], and gray level co-occurrence matrix (GLCM) [ 44 ]. Some research efforts have been developed to speed up the features extraction process in parallel using GPU as our previous research work in [ 47 ]. The second stage feeds the feature vector into a classifier model that trained in advance to detect whether the input image has a defect or not [ 16 ].…”

Section: Related Workmentioning

confidence: 99%

DSTEELNet: A Real-Time Parallel Dilated CNN with Atrous Spatial Pyramid Pooling for Detecting and Classifying Defects in Surface Steel Strips

Ahmed

2023

Sensors

View full text Add to dashboard Cite

Automatic defects inspection and classification demonstrate significant importance in improving quality in the steel industry. This paper proposed and developed DSTEELNet convolution neural network (CNN) architecture to improve detection accuracy and the required time to detect defects in surface steel strips. DSTEELNet includes three parallel stacks of convolution blocks with atrous spatial pyramid pooling. Each convolution block used a different dilation rate that expands the receptive fields, increases the feature resolutions and covers square regions of input 2D image without any holes or missing edges and without increases in computations. This work illustrates the performance of DSTEELNet with a different number of parallel stacks and a different order of dilation rates. The experimental results indicate significant improvements in accuracy and illustrate that the DSTEELNet achieves of 97% mAP in detecting defects in surface steel strips on the augmented dataset GNEU and Severstal datasets and is able to detect defects in a single image in 23ms.

show abstract