Texture Recognition and Classification Based on Deep Learning

Zhu, Gaoming; Li, Bingchan; Hong, Shuai; Mao, Bo

doi:10.1109/cbd.2018.00068

Cited by 8 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve the problem of color contrast and distortion which is usually observed in underwater images, a method of using CNN for converting the image to gray scale and to restore hue is been proposed [5]. To increase the generalization ability of texture-based image classification, data augmentation of deep learning is applied, the method significantly increases the accuracy [6]. Another method for dynamic texture-based classification, where features are extracted using pre-trained CNN which is later fed into SVM for classification [7].…”

Section: Related Workmentioning

confidence: 99%

Learning Semantic Features for Classifying Very Large Image Datasets Using Convolution Neural Network

Rao¹,

Kapanaiah²

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Advancements in sensors and image acquisition devices lead to tremendous increase in creation of unlabeled database of images, and traditional image retrieval approaches are inefficient in retrieving semantic images. Neural network is emerging as popular method to solve most of the state-of-the-art problems in filling the gap between low level features and high level semantics. Convolution neural network (CNN) is a category of neural network which automatically extracts the important features without any human intervention, with considerably reduced set of parameters. In this paper, a model is generated using CNN (VGG-16) architecture which combines convolution and max pooling layers at different levels using effective regularization and transfer learning with data augmentation. The effectiveness of proposed model is demonstrated on benchmarking Caltech 101 and 256 datasets. The results obtained have proven the capacity of model in understanding high level semantics and outperformed several contemporary techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Semantic Features for Classifying Very Large Image Datasets Using Convolution Neural Network

Rao¹,

Kapanaiah²

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

show abstract

“…The unsupervised classification methods include the well-known K-means, hierarchical clustering, Self-Organizing Maps (SOM) and Dynamic Time Warping (DTW) techniques [19]. Additionally, the deep learning models and graph clustering algorithms represent effective unsupervised classification solutions that can be applied successfully to texture recognition [20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Automatic Unsupervised Texture Recognition Framework Using Anisotropic Diffusion-Based Multi-Scale Analysis and Weight-Connected Graph Clustering

Barbu¹

2021

Symmetry

View full text Add to dashboard Cite

A novel unsupervised texture classification technique is proposed in this research work. The proposed method clusters automatically the textures of an image collection in similarity classes whose number is not a priori known. A nonlinear diffusion-based multi-scale texture analysis approach is introduced first. It creates an effective scale-space by using a well-posed anisotropic diffusion filtering model that is proposed and approximated numerically here. A feature extraction process using a bank of circularly symmetric 2D filters is applied at each scale, then a rotation-invariant texture feature vector is achieved for the current image by combining the feature vectors computed at all these scales. Next, a weighted similarity graph, whose vertices correspond to the texture feature vectors and the weights of its edges are obtained from the distances computed between these vectors, is created. A novel weighted graph clustering technique is then applied to this similarity graph, to determine the texture classes. Numerical simulations and method comparisons illustrating the effectiveness of the described framework are also discussed in this work.

show abstract

“…: Tech. 68(6) 2020 R. Kapela sented here can be found in [9][10][11] where focus of the first two is on the effective feature extraction for further accurate classification. This way in [9] we can observe the usage of LBP again as a pre-processing technique but this time inside a deep architecture of a neural network.…”

Section: Introductionmentioning

confidence: 99%

“…Both systems are featured with high recognition accuracy but they lack the ability to recognize multiple texture classes in the same image. Zhu et al [11] on the other hand deal with the problem of data augmentation which is very common in training the models with tens of millions of parameters. The system described in this work has very similar advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

Bulletin of the Polish Academy of Sciences: Technical Sciences

Kapela¹

2020

View full text Add to dashboard Cite

This paper presents a deep learning-based image texture recognition system. The methodology taken in this solution is formed in a bottom-up manner. It means we swipe a moving window through the image in order to categorize if a given region belongs to one of the classes seen in the training process. This categorization is done based on the Deep Neural Network (DNN) of fixed architecture. The training process is fully automated regarding the training data preparation, investigation of the best training algorithm, and its hyper-parameters. The only human input to the system is the definition of the categories for further recognition and generation of the samples (region markings) in the external application chosen by the user. The system is tested on road surface images where its task is to categorize image regions to a different road category (e.g. curb, road surface damage, etc.) and is featured with 90% and above accuracy.

show abstract

Texture Recognition and Classification Based on Deep Learning

Cited by 8 publications

References 3 publications

Learning Semantic Features for Classifying Very Large Image Datasets Using Convolution Neural Network

Learning Semantic Features for Classifying Very Large Image Datasets Using Convolution Neural Network

Automatic Unsupervised Texture Recognition Framework Using Anisotropic Diffusion-Based Multi-Scale Analysis and Weight-Connected Graph Clustering

Bulletin of the Polish Academy of Sciences: Technical Sciences

Contact Info

Product

Resources

About