An Apparatus and Method for Real-Time Stacked Sheets Counting With Line-Scan Cameras

Chen, Tiejian; Wang, Yaonan; Xiao, Changyan

doi:10.1109/tim.2014.2366977

Cited by 14 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the papers are counted by detecting the paper boundaries. In the experiments, the proposed method achieved higher performance than the latest related work, namely Chen's method . Nevertheless, the average processing time was about 3.5 s. This is slow for practical use.…”

Section: Introductionmentioning

confidence: 83%

“…In order to investigate the effectiveness of the proposed method, we conducted experiments using the constructed dataset. Also, the proposed method was compared with our previous method and Chen's method .…”

Section: Methodsmentioning

confidence: 99%

“…Chen et al . proposed a signal processing approach using a line‐scan camera . First of all, a stack of paper was captured by the line scan camera, and a one‐dimensional image was obtained.…”

Section: Related Workmentioning

confidence: 99%

“…The papers were arranged manually. The space of each paper was mm. Since this manual arrangement is hard work, a robot will be developed in the future.…”

Section: Construction Of a Facial Oil Blotting Paper Datasetmentioning

confidence: 99%

See 3 more Smart Citations

Vision‐based facial oil blotting paper counting

Sato

Yamada

Ito

et al. 2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

In the production of facial oil blotting papers, a certain number of papers must be counted before packaging. Currently, the papers are counted by hand, and this is hard work. Also, there are risks of adhesion of dust and wrinkles. In order to solve these problems, we propose a vision-based approach. After the papers, which are arranged by shifting, are captured, the proposed image processing steps detect the boundaries of the papers. By counting the detected boundaries, the number of papers can be counted. Since the parameters for the proposed image processing are optimized by genetic algorithm, prior setting by a user is not necessary. For the experiments, an image dataset was constructed with six types of facial oil blotting papers. The proposed method achieved higher F-measure than in other related works.

show abstract

Section: Introductionmentioning

confidence: 83%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…The papers were arranged manually. The space of each paper was mm. Since this manual arrangement is hard work, a robot will be developed in the future.…”

Section: Construction Of a Facial Oil Blotting Paper Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Vision‐based facial oil blotting paper counting

Sato

Yamada

Ito

et al. 2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…In this system, the camera array was used to capture the edge texture of the packing paper, then these texture images were processed by image processing algorithm. Chen, T. et al [2]. accurately count stacked-sheet in real time based on line-scan cameras and counting algorithm.…”

Section: Introductionmentioning

confidence: 99%

A non-contact method for real-time stacked- sheet counting based on broadband X-ray absorption spectra and LSTM model

Zheng

Yuan

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

In order to count stacked-sheet in real time, a non-contact method based on broadband X-ray absorption spectra (XAS) and long short-term memory (LSTM) network was proposed. Five hundred sheets of standard A4 printing papers (70 g/m2) were taken as experimental samples. The broadband XAS detection equipment was used to scan the papers leading to 500 broadband XAS data, and the data were preprocessed by principal component analysis (PCA). LSTM was built to count stacked papers, and compared with polynomial fitting model(PFM) and artificial neural network (ANN) to verify the difference in prediction accuracy. Mean square error (MSE), Mean absolute error (MAE), Max-error (MAXE) and Coefficient of determination (R2) were selected as evaluation indexes of above models. The experimental results showed that the proposed approach can count stacked-sheet accurately with the MAE was 1.0895 and the prediction time was less than 0.006 second. All the index results of LSTM were better than those of PFM and ANN. Therefore, this study using broadband XAS and LSTM realized real-time stacked-sheet counting, and provided a new idea for thickness measurement field.

show abstract