scholarly journals Image Segmentation Using Encoder-Decoder with Deformable Convolutions

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1570
Author(s):  
Andreea Gurita ◽  
Irina Georgiana Mocanu
Keyword(s):  
Neural Network ◽  
Image Analysis ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Data Augmentation ◽  
Real Life ◽  
Semantic Segmentation ◽  
Essential Step ◽  
Augmentation Techniques ◽  
Made In

Image segmentation is an essential step in image analysis that brings meaning to the pixels in the image. Nevertheless, it is also a difficult task due to the lack of a general suited approach to this problem and the use of real-life pictures that can suffer from noise or object obstruction. This paper proposes an architecture for semantic segmentation using a convolutional neural network based on the Xception model, which was previously used for classification. Different experiments were made in order to find the best performances of the model (eg. different resolution and depth of the network and data augmentation techniques were applied). Additionally, the network was improved by adding a deformable convolution module. The proposed architecture obtained a 76.8 mean IoU on the Pascal VOC 2012 dataset and 58.1 on the Cityscapes dataset. It outperforms SegNet and U-Net networks, both networks having considerably more parameters and also a higher inference time.

scholarly journals DMCNN: A Deep Multiscale Convolutional Neural Network Model for Medical Image Segmentation

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Lin Teng ◽  
Hang Li ◽  
Shahid Karim
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Medical Image ◽  
Data Augmentation ◽  
Medical Images ◽  
Medical Image Segmentation ◽  
Related Area ◽  
Segmentation Accuracy

Medical image segmentation is one of the hot issues in the related area of image processing. Precise segmentation for medical images is a vital guarantee for follow-up treatment. At present, however, low gray contrast and blurred tissue boundaries are common in medical images, and the segmentation accuracy of medical images cannot be effectively improved. Especially, deep learning methods need more training samples, which lead to time-consuming process. Therefore, we propose a novelty model for medical image segmentation based on deep multiscale convolutional neural network (CNN) in this article. First, we extract the region of interest from the raw medical images. Then, data augmentation is operated to acquire more training datasets. Our proposed method contains three models: encoder, U-net, and decoder. Encoder is mainly responsible for feature extraction of 2D image slice. The U-net cascades the features of each block of the encoder with those obtained by deconvolution in the decoder under different scales. The decoding is mainly responsible for the upsampling of the feature graph after feature extraction of each group. Simulation results show that the new method can boost the segmentation accuracy. And, it has strong robustness compared with other segmentation methods.

scholarly journals Rethinking Separable Convolutional Encoders for End-to-End Semantic Image Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Lin Wang ◽  
Xingfu Wang ◽  
Ammar Hawbani ◽  
Yan Xiong ◽  
Xu Zhang
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Image Data ◽  
Semantic Segmentation ◽  
Semantic Features ◽  
Processing Efficiency ◽  
Semantic Image Segmentation ◽  
Average Improvement ◽  
Convolutional Encoders

With the development of science and technology, the middle volume and neural network in the semantic image segmentation of the codec show good development prospects. Its advantage is that it can extract richer semantic features, but this will cause high costs. In order to solve this problem, this article mainly introduces the codec based on a separable convolutional neural network for semantic image segmentation. This article proposes a codec based on a separable convolutional neural network for semantic image segmentation research methods, including the traditional convolutional neural network hierarchy into a separable convolutional neural network, which can reduce the cost of image data segmentation and improve processing efficiency. Moreover, this article builds a separable convolutional neural network codec structure and designs a semantic segmentation process, so that the codec based on a separable convolutional neural network is used for semantic image segmentation research experiments. The experimental results show that the average improvement of the dataset by the improved codec is 0.01, which proves the effectiveness of the improved SegProNet. The smaller the number of training set samples, the more obvious the performance improvement.

Data augmentation techniques for transfer learning improvement in drill wear classification using convolutional neural network

2019 ◽  
Vol 28 (1) ◽  
pp. 3-12
Author(s):  
Jarosław Kurek ◽  
Joanna Aleksiejuk-Gawron ◽  
Izabella Antoniuk ◽  
Jarosław Górski ◽  
Albina Jegorowa ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Good Condition ◽  
Training Data ◽  
Time Data ◽  
Learning Improvement ◽  
Original Dataset ◽  
Augmentation Techniques

This paper presents an improved method for recognizing the drill state on the basis of hole images drilled in a laminated chipboard, using convolutional neural network (CNN) and data augmentation techniques. Three classes were used to describe the drill state: red -- for drill that is worn out and should be replaced, yellow -- for state in which the system should send a warning to the operator, indicating that this element should be checked manually, and green -- denoting the drill that is still in good condition, which allows for further use in the production process. The presented method combines the advantages of transfer learning and data augmentation methods to improve the accuracy of the received evaluations. In contrast to the classical deep learning methods, transfer learning requires much smaller training data sets to achieve acceptable results. At the same time, data augmentation customized for drill wear recognition makes it possible to expand the original dataset and to improve the overall accuracy. The experiments performed have confirmed the suitability of the presented approach to accurate class recognition in the given problem, even while using a small original dataset.

scholarly journals A Dual-Path and Lightweight Convolutional Neural Network for High-Resolution Aerial Image Segmentation

2019 ◽  
Vol 8 (12) ◽  
pp. 582 ◽  
Author(s):  
Gang Zhang ◽  
Tao Lei ◽  
Yi Cui ◽  
Ping Jiang
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Feature Learning ◽  
Semantic Segmentation ◽  
Aerial Images ◽  
Aerial Image ◽  
Sensing Applications ◽  
Edge Path

Semantic segmentation on high-resolution aerial images plays a significant role in many remote sensing applications. Although the Deep Convolutional Neural Network (DCNN) has shown great performance in this task, it still faces the following two challenges: intra-class heterogeneity and inter-class homogeneity. To overcome these two problems, a novel dual-path DCNN, which contains a spatial path and an edge path, is proposed for high-resolution aerial image segmentation. The spatial path, which combines the multi-level and global context features to encode the local and global information, is used to address the intra-class heterogeneity challenge. For inter-class homogeneity problem, a Holistically-nested Edge Detection (HED)-like edge path is employed to detect the semantic boundaries for the guidance of feature learning. Furthermore, we improve the computational efficiency of the network by employing the backbone of MobileNetV2. We enhance the performance of MobileNetV2 with two modifications: (1) replacing the standard convolution in the last four Bottleneck Residual Blocks (BRBs) with atrous convolution; and (2) removing the convolution stride of 2 in the first layer of BRBs 4 and 6. Experimental results on the ISPRS Vaihingen and Potsdam 2D labeling dataset show that the proposed DCNN achieved real-time inference speed on a single GPU card with better performance, compared with the state-of-the-art baselines.

scholarly journals Detection of Melanoma Skin Cancer using Convolutional Neural Network algorithm

2020 ◽  
Vol 9 (7) ◽  
pp. 115-118
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Skin Cancer ◽  
Skin Lesion ◽  
Convolutional Neural Network ◽  
Data Augmentation ◽  
Health Sector ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Melanoma Skin

Skin Cancer, a health issue which might cause severe consequences if not detected and controlled properly. Since there is a huge evolution in the health sector because of development in computer technologies, it is possible to analyze images efficiently and make correct decisions. Deep learning algorithms can be used for analyzing dermoscopic images by learning features of images in an incremental manner. Aim of our proposed method is to categorize skin lesion image as Benign or Melanoma and also to study the performance of Convolutional Neural Network algorithm using data augmentation technique and without data augmentation technique. The proposed method uses dataset from ISIC archive 2019. Steps involved in the proposed method are Image Pre-Processing, Image Segmentation and Image Classification. Initially, Image Pre-Processing algorithm is performed on skin lesion image. Image Segmentation algorithm is used to obtain Region of Interest (ROI) from pre-processed image. Then, Convolutional Neural Network algorithm classifies image as melanoma or benign. The Proposed method can rapidly detect melanoma skin cancer which aids in starting the treatment process without delay.

Fault Detection in Soft-started Induction Motors using Convolutional Neural Network Enhanced by Data Augmentation Techniques

2021 ◽  
Author(s):  
Dario Pasqualotto ◽  
Angela Navarro Navarro ◽  
Mauro Zigliotto ◽  
Jose A. Antonino-Daviu ◽  
Vicente Biot-Monterde
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Convolutional Neural Network ◽  
Data Augmentation ◽  
Induction Motors ◽  
Augmentation Techniques

scholarly journals R2AU-Net: Attention Recurrent Residual Convolutional Neural Network for Multimodal Medical Image Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Qiang Zuo ◽  
Songyu Chen ◽  
Zhifang Wang
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Medical Image ◽  
Data Science ◽  
Contextual Information ◽  
Semantic Segmentation ◽  
Medical Image Segmentation ◽  
Segmentation Method ◽  
Public Dataset

In recent years, semantic segmentation method based on deep learning provides advanced performance in medical image segmentation. As one of the typical segmentation networks, U-Net is successfully applied to multimodal medical image segmentation. A recurrent residual convolutional neural network with attention gate connection (R2AU-Net) based on U-Net is proposed in this paper. It enhances the capability of integrating contextual information by replacing basic convolutional units in U-Net by recurrent residual convolutional units. Furthermore, R2AU-Net adopts attention gates instead of the original skip connection. In this paper, the experiments are performed on three multimodal datasets: ISIC 2018, DRIVE, and public dataset used in LUNA and the Kaggle Data Science Bowl 2017. Experimental results show that R2AU-Net achieves much better performance than other improved U-Net algorithms for multimodal medical image segmentation.

scholarly journals Random Erasing Data Augmentation

2020 ◽  
Vol 34 (07) ◽  
pp. 13001-13008 ◽  
Author(s):  
Zhun Zhong ◽  
Liang Zheng ◽  
Guoliang Kang ◽  
Shaozi Li ◽  
Yi Yang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Data Augmentation ◽  
Parameter Learning ◽  
Identification Code ◽  
Training Images ◽  
Augmentation Techniques

In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly used data augmentation techniques such as random cropping and flipping, and yields consistent improvement over strong baselines in image classification, object detection and person re-identification. Code is available at: https://github.com/zhunzhong07/Random-Erasing.

Sign in / Sign up

Export Citation Format

Share Document