Macroscopic Rock Texture Image Classification Using a Hierarchical Neuro‐Fuzzy Class Method

Gonçalves, Laercio B; Leta, Fabiana Rodrigues

doi:10.1155/2010/163635

Cited by 9 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of a consumer choosing stone flooring is actually the process of their brain consciousness extracting and summarizing the qualities of marble, followed by their conscious preference to actively match the sample characteristics they have extracted to complete their selection of decorative stone flooring. Using binary space division, Gonçalves et al developed a hierarchical neuro-fuzzy classification approach for classifying macroscopic rock textures [37]. The images can be transformed to HSV color space, a small number of representative colors are quantified, and texture characteristics are retrieved based on the uniform pattern of rotated RLBP (rotated local binary pattern) [38].…”

Section: Visual Imagery Evaluation Methodsmentioning

confidence: 99%

Research on Green Consumption Based on Visual Evaluation Method—Evidence from Stone Flooring Industry

Chen

2023

Sustainability

View full text Add to dashboard Cite

Blind consumption discovered in the real application of flooring does not produce the visually anticipated impression, leading to additional time costs and stone flooring waste. Consumers cannot clearly articulate their visual imaging needs when purchasing stone flooring. Due to consumers’ lack of understanding of the visual imagery style of decorative stone flooring, manufacturers are unable to produce more visual styles of stone flooring in response to consumer demand, which leads to an unorganized production process and the wasting of stone resources. Additionally, manufacturers are unable to receive feedback on market demand, which makes communication links between sales teams difficult. A total of 40 adjectives were considered the most appropriate in a pool of 110 adjectives for the visual imagery evaluation of stone after ten interior design professionals with experience in decorative stone applications had narrowed the selection. Following this, a general consumer semantic difference method questionnaire survey and questionnaire data factor analysis statistics were used to create 10 sets of visual imagery adjectives for marble flooring, which were then divided into 10 different types of marble flooring. Following the computer simulation drawing with the 10 groups of visual imagery adjectives design questionnaire, the consumers completed the visual imagery evaluation questionnaire survey. They received a 304-question valid questionnaire, and using the triangular fuzzy number operation in fuzzy theory, they arrived at 10 marble floors in the visual imagery evaluation score. In order to clarify the current consumer demand for stone floor imagery, the high sales volume of stone flooring on the market for visual style division, which can guide consumers according to their visual needs for an efficient choice, can enhance the efficiency of communication between consumers and sellers. It can also help enterprises clarify the market consumer demand for orderly production to achieve the purpose of green consumption and to ensure the sustainable development of the decorative stone flooring market.

show abstract

Section: Visual Imagery Evaluation Methodsmentioning

confidence: 99%

Research on Green Consumption Based on Visual Evaluation Method—Evidence from Stone Flooring Industry

Chen

2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…To represent constraint states of an activity different textures can be used. Texture can encode information [11] by using color channel, tilling, smoothness, and many other attributes. Due to these different encodings a texture is suitable to represent different constraint states with ease.…”

Section: Processmentioning

confidence: 99%

Evaluating Compliance State Visualizations for Multiple Process Models and Instances

Gall

Rinderle-Ma

2021

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Business process compliance refers to the formalization, enactment, verification, and monitoring of constraints for one or multiple process models and one or multiple process instances. Such complex compliance scenarios crave for visualization support that fosters traceability and understandability during design and runtime. It must be clear, for example, which processes and process instances are subject to which compliance constraint and, especially during runtime, which compliance state (e.g., satisfied or violated) is active. This paper analyzes existing visualization approaches for compliance-related information and demonstrates their usability and feasibility through a prototypical implementation and the application to a logistics scenario. The focus is on constraints that span across multiple processes and process instances. The preferred visualizations are then implemented in a real-world process scenario from the manufacturing domain and evaluated through in-depth interviews with three stakeholders. The interviews narrow down the results of the technical evaluation, indicating that Color is best suited for obtaining a quick overview and Text for in-detail analysis of compliance states.

show abstract

“…Singh et al (2010) used a multilayer perceptron to extract 27 features from basalt rock slice images and achieved the classification of 140 rock sample slice images. Gonçalves and Leta (2010) proposed a neuro-fuzzy hierarchical classification method based on binary space division for macroscopic rock structure classification, and the final classification accuracy reached 73%. Młynarczuk et al (2013) used the nearest neighbor algorithm and k-nearest neighbor algorithm to realize the classification of 9 different types of rocks.…”

Section: Introductionmentioning

confidence: 99%

Rock image classification using deep residual neural network with transfer learning

Chen

Su²,

Chen³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Rock image classification is a significant part of geological research. Compared with traditional image classification methods, rock image classification methods based on deep learning models have the great advantage in terms of automatic image features extraction. However, the rock classification accuracies of existing deep learning models are unsatisfied due to the weak feature extraction ability of the network model. In this study, a deep residual neural network (ResNet) model with the transfer learning method is proposed to establish the corresponding rock automatic classification model for seven kinds of rock images. ResNet34 introduces the residual structure to make it have an excellent effect in the field of image classification, which extracts high-quality rock image features and avoids information loss. The transfer learning method abstracts the deep features from the shallow features, and better express the rock texture features for classification in the case of fewer rock images. To improve the generalization of the model, a total of 3,82,536 rock images were generated for training via image slicing and data augmentation. The network parameters trained on the Texture Library dataset which contains 47 types of texture images and reflect the characteristics of rocks are used for transfer learning. This pre-trained weight is loaded when training the ResNet34 model with the rock dataset. Then the model parameters are fine-tuned to transfer the model to the rock classification problem. The experimental results show that the accuracy of the model without transfer learning reached 88.1%, while the model using transfer learning achieved an accuracy of 99.1%. Aiming at geological engineering field investigation, this paper studies the embedded deployment application of the rock classification network. The proposed rock classification network model is transplanted to an embedded platform. By designing a rock classification system, the off-line rock classification is realized, which provides a new solution for the rock classification problem in the geological survey. The deep residual neural network and transfer learning method used in this paper can automatically classify rock features without manually extracting. These methods reduce the influence of subjective factors and make the rock classification process more automatic and intelligent.

show abstract

Macroscopic Rock Texture Image Classification Using a Hierarchical Neuro‐Fuzzy Class Method

Cited by 9 publications

References 27 publications

Research on Green Consumption Based on Visual Evaluation Method—Evidence from Stone Flooring Industry

Research on Green Consumption Based on Visual Evaluation Method—Evidence from Stone Flooring Industry

Evaluating Compliance State Visualizations for Multiple Process Models and Instances

Rock image classification using deep residual neural network with transfer learning

Contact Info

Product

Resources

About