Deep Multimodel Cascade Method Based on CNN and Random Forest for Pharmaceutical Particle Detection

Zhang, Hui; Zhao, Miao; Liu, Li; Zhong, Huicai; Liang, Zhicong; Yang, Yimin; Zhou, Xianen; Wu, Q. M. Jonathan

doi:10.1109/tim.2020.2973843

Cited by 26 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tsai and Chou proposed four CNN-based models for precise positioning in PCB manufacturing and production to achieve exact position and angle detection [ 28 ]. Zhang et al proposed a deep multimodel cascade method that combines single-frame image and multiframe image processing to detect and identify foreign particles for the qualitative detection of liquid pharmaceutical products [ 29 ]. Zhang et al proposed a method that combines Faster R-CNN and R-FCN multichannel features to detect surface defects in the production process of solar panels [ 30 ].…”

Section: Related Workmentioning

confidence: 99%

Research on Object Detection of PCB Assembly Scene Based on Effective Receptive Field Anchor Allocation

Chen

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Vision-based object detection of PCB (printed circuit board) assembly scenes is essential in accelerating the intelligent production of electronic products. In particular, it is necessary to improve the detection accuracy as much as possible to ensure the quality of assembly products. However, the lack of object detection datasets in PCB assembly scenes is the key to restricting intellectual PCB assembly research development. As an excellent representative of the one-stage object detection model, YOLOv3 (you only look once version 3) mainly relies on placing predefined anchors on the three feature pyramid layers and realizes recognition and positioning using regression. However, the number of anchors distributed in each grid cell of different scale feature layers is usually the same. The ERF (effective receptive field) corresponding to the grid cell at different locations varies. The contradiction between the uniform distribution of fixed-size anchors and the ERF size range in different feature layers will reduce the effectiveness of object detection. Few people use ERF as a standard for assigning anchors to improve detection accuracy. To address this issue, firstly, we constructed a PCB assembly scene object detection dataset, which includes 21 classes of detection objects in three scenes before assembly, during assembly, and after assembly. Secondly, we performed a refined ERF analysis on each grid of the three output layers of YOLOv3, determined the ERF range of each layer, and proposed an anchor allocation rule based on the ERF. Finally, for the small and difficult-to-detect TH (through-holes), we increased the context information and designed improved-ASPP (Atrous spatial pyramid pooling) and channel attention joint module. Through a series of experiments on the object detection dataset of the PCB assembly scene, we found that under the framework of YOLOv3, anchor allocation based on ERF can increase mAP (mean average precision) from 79.32% to 89.86%. At the same time, our proposed method is superior to Faster R-CNN (region convolution neural network), SSD (single shot multibox detector), and YOLOv4 (you only look once version 4) in the balance of high detection accuracy and low computational complexity.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on Object Detection of PCB Assembly Scene Based on Effective Receptive Field Anchor Allocation

Chen

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The accuracy of positioning error is improved. In terms of abnormal detection of pharmaceutical products by robots, Zhang [36] proposes a multi-model cascade method of drug particle detection depth based on CNN and random forest. For small foreign particles in liquid medicine, a multi-model cascade method of single frame combined with multi-frame images is adopted.…”

Section: Application Scenarios Of Robots In Pharmaceutical Industrymentioning

confidence: 99%

A Review of Pharmaceutical Robot based on Hyperspectral Technology

Wang

Mao

et al. 2022

J Intell Robot Syst

Self Cite

View full text Add to dashboard Cite

The quality and safety of medicinal products are related to patients’ lives and health. Therefore, quality inspection takes a key role in the pharmaceutical industry. Most of the previous solutions are based on machine vision, however, their performance is limited by the RGB sensor. The pharmaceutical visual inspection robot combined with hyperspectral imaging technology is becoming a new trend in the high-end medical quality inspection process since the hyperspectral data can provide spectral information with spatial knowledge. Yet, there is no comprehensive review about hyperspectral imaging-based medicinal products inspection. This paper focuses on the pivotal pharmaceutical applications, including counterfeit drugs detection, active component analysis of tables, and quality testing of herbal medicines and other medical materials. We discuss the technology and hardware of Raman spectroscopy and hyperspectral imaging, firstly. Furthermore, we review these technologies in pharmaceutical scenarios. Finally, the development tendency and prospect of hyperspectral imaging technology-based robots in the field of pharmaceutical quality inspection is summarized.

show abstract

“…To the best of our knowledge, there has not been a study that directly address the problem equivalent to pTSC, where both variable length and variable time offset are included. In the existing work on liquid inspection, trajectory data are simply classified using handcraft features without accounting for timestamp differences [13].…”

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series

Sawada¹,

Miyagawa²,

Ebihara³

et al. 2022

Preprint

View full text Add to dashboard Cite

Time series data are often obtained only within a limited time range due to interruptions during observation process. To classify such partial time series, we need to account for 1) the variable-length data drawn from 2) different timestamps. To address the first problem, existing convolutional neural networks use global pooling after convolutional layers to cancel the length differences. This architecture suffers from the trade-off between incorporating entire temporal correlations in long data and avoiding feature collapse for short data. To resolve this tradeoff, we propose Adaptive Multi-scale Pooling, which aggregates features from an adaptive number of layers, i.e., only the first few layers for short data and more layers for long data. Furthermore, to address the second problem, we introduce Temporal Encoding, which embeds the observation timestamps into the intermediate features. Experiments on our private dataset and the UCR/UEA time series archive show that our modules improve classification accuracy especially on short data obtained as partial time series.

show abstract

Deep Multimodel Cascade Method Based on CNN and Random Forest for Pharmaceutical Particle Detection

Cited by 26 publications

References 33 publications

Research on Object Detection of PCB Assembly Scene Based on Effective Receptive Field Anchor Allocation

Research on Object Detection of PCB Assembly Scene Based on Effective Receptive Field Anchor Allocation

A Review of Pharmaceutical Robot based on Hyperspectral Technology

Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series

Contact Info

Product

Resources

About