Generating integrated bill of materials using mask R-CNN artificial intelligence model

Chowdhury, Ayesha Munira; Moon, Soo Young

doi:10.1016/j.autcon.2022.104644

Cited by 12 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The user end is responsible for interacting with the user to upload the target image and display the recognition results. The server is responsible for deploying deep learning algorithms, including image classification, text detection, text recognition, and text extraction modules [5][6][7].…”

Section: The Basic Process Of Bill Recognitionmentioning

confidence: 99%

Intelligent Extraction of Financial Bill Information Based on LeNet

Cao

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

To improve the recognition efficiency of financial bills, this paper proposes an improved LeNet algorithm to achieve higher digit recognition performance. We carefully study the characteristics of convolutional neural networks and analyze the defects of existing LeNet for the content recognition of financial bills. Based on the actual needs of financial bill recognition, the number of convolutional kernels in the LeNet sub network are increased to enhance the network’s ability and distinguish different bill images. Then, the improvement of the LeNet network structure is achieved by using a shallow convolutional structure and a better performance Relu activation function. Then, the research and performance verification of the algorithm for bill text detection and recognition are conducted on the actual dataset. The results show that the proposed method can effectively identify printed bills with strong interference in complex environments, with an accuracy of over 96% and a recognition rate of 1.136 s/sheet. Compared with traditional algorithms, the improved LeNet-5 algorithm has been significantly improved in terms of reducing detection time and recognition rate.

show abstract

Section: The Basic Process Of Bill Recognitionmentioning

confidence: 99%

Intelligent Extraction of Financial Bill Information Based on LeNet

Cao

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

show abstract

“…Mask–RCNN offers more precise and accurate results [ 40 ]; however, in some cases, it takes around 48 h to train the system. Numerous public databases such as Common Objects in Context (COCO) are available with training weights to train systems using the transfer learning approach [ 41 , 42 ]. Overall, Mask–RCNN is an effective tool for image analyses and has the potential for further advancements in computer vision.…”

Section: Introductionmentioning

confidence: 99%

Fully Automated Skull Stripping from Brain Magnetic Resonance Images Using Mask RCNN-Based Deep Learning Neural Networks

Azam,

Tariq,

Shehzad

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

This research comprises experiments with a deep learning framework for fully automating the skull stripping from brain magnetic resonance (MR) images. Conventional techniques for segmentation have progressed to the extent of Convolutional Neural Networks (CNN). We proposed and experimented with a contemporary variant of the deep learning framework based on mask region convolutional neural network (Mask–RCNN) for all anatomical orientations of brain MR images. We trained the system from scratch to build a model for classification, detection, and segmentation. It is validated by images taken from three different datasets: BrainWeb; NAMIC, and a local hospital. We opted for purposive sampling to select 2000 images of T1 modality from data volumes followed by a multi-stage random sampling technique to segregate the dataset into three batches for training (75%), validation (15%), and testing (10%) respectively. We utilized a robust backbone architecture, namely ResNet–101 and Functional Pyramid Network (FPN), to achieve optimal performance with higher accuracy. We subjected the same data to two traditional methods, namely Brain Extraction Tools (BET) and Brain Surface Extraction (BSE), to compare their performance results. Our proposed method had higher mean average precision (mAP) = 93% and content validity index (CVI) = 0.95%, which were better than comparable methods. We contributed by training Mask–RCNN from scratch for generating reusable learning weights known as transfer learning. We contributed to methodological novelty by applying a pragmatic research lens, and used a mixed method triangulation technique to validate results on all anatomical modalities of brain MR images. Our proposed method improved the accuracy and precision of skull stripping by fully automating it and reducing its processing time and operational cost and reliance on technicians. This research study has also provided grounds for extending the work to the scale of explainable artificial intelligence (XAI).

show abstract

“…Digital work instructions can be partially generated using artificial intelligence from CAD model BOMs (Bill of Material) [42] or a BOM of a recognized object can be generated [43,44]. Several tests of the automatic generation of augmented reality generated product assembly workflows have been performed, showing that it is possible, albeit with technological limitations, to machine-generate an augmented reality instruction manual [45].…”

Section: Introductionmentioning

confidence: 99%

Methodology for Rationalization of Pre-Production Processes Using Virtual Reality Based Manufacturing Instructions

Novikov,

Hořejší,

Kubr

et al. 2023

Machines

View full text Add to dashboard Cite

This article deals with the rationalization of manufacturing processes within the product life cycle with emphasis on the pre-production phase of production. A new methodology for evaluating the applicability of modern visualization tools in manufacturing processes is presented. This methodology includes a modified Z-score for categorizing manufacturing processes and has been validated by the successful implementation of 10 real projects. Ultimately, the methodology provides a practical decision-making aid for manufacturing companies in deploying such Computer Aided Instruction tools. For the pre-production phase of products and their development, the possibilities of using modern visualization tools to support CAD instructions and assembly instructions are being explored. These modern visualization tools are video tutorials, augmented reality tutorials and virtual reality tutorials. This paper explores the use of these tools for rationalization of pre-production processes. A methodology was designed to select the most appropriate tool for rationalizing process execution in preparation for production. The functionality of the methodology was verified by applying the methodology in industrial practice and subsequent implementation of the recommended solutions. The methodology was validated by testing key combinations that can arise based on the methodology directly in the operations of manufacturing companies. A total of 10 implementations in real production processes were tailored to this study and carried out over 2 years and the functionality of the methodology was confirmed (that consisted also of a new software development). It was found that there is a dependency between the visualization tools chosen to create the instructions in the context of organizational production preparation and the nature of the production processes.

show abstract

Generating integrated bill of materials using mask R-CNN artificial intelligence model

Cited by 12 publications

References 16 publications

Intelligent Extraction of Financial Bill Information Based on LeNet

Intelligent Extraction of Financial Bill Information Based on LeNet

Fully Automated Skull Stripping from Brain Magnetic Resonance Images Using Mask RCNN-Based Deep Learning Neural Networks

Methodology for Rationalization of Pre-Production Processes Using Virtual Reality Based Manufacturing Instructions

Contact Info

Product

Resources

About