Research on Text Location and Recognition in Natural Images with Deep Learning

2018 ◽  
Author(s):  
Ping Zhang ◽  
Ziyu Shi ◽  
Haichang Gao
Keyword(s):  
Deep Learning ◽  
Natural Images ◽  
Text Location

Learning About the World by Learning About Images

2021 ◽  
pp. 096372142199033
Author(s):  
Katherine R. Storrs ◽  
Roland W. Fleming
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Visual Processing ◽  
Visual Experience ◽  
Natural Images ◽  
Sensory Coding ◽  
The World ◽  
Unsupervised Deep Learning ◽  
Statistical Regularities ◽  
Sensory Encoding

One of the deepest insights in neuroscience is that sensory encoding should take advantage of statistical regularities. Humans’ visual experience contains many redundancies: Scenes mostly stay the same from moment to moment, and nearby image locations usually have similar colors. A visual system that knows which regularities shape natural images can exploit them to encode scenes compactly or guess what will happen next. Although these principles have been appreciated for more than 60 years, until recently it has been possible to convert them into explicit models only for the earliest stages of visual processing. But recent advances in unsupervised deep learning have changed that. Neural networks can be taught to compress images or make predictions in space or time. In the process, they learn the statistical regularities that structure images, which in turn often reflect physical objects and processes in the outside world. The astonishing accomplishments of unsupervised deep learning reaffirm the importance of learning statistical regularities for sensory coding and provide a coherent framework for how knowledge of the outside world gets into visual cortex.

scholarly journals A Natural Images Pre-Trained Deep Learning Method for Seismic Random Noise Attenuation

2022 ◽  
Vol 14 (2) ◽  
pp. 263
Author(s):  
Haixia Zhao ◽  
Tingting Bai ◽  
Zhiqiang Wang
Keyword(s):  
Deep Learning ◽  
Seismic Data ◽  
Field Data ◽  
Noise Suppression ◽  
Signal To Noise Ratio ◽  
Random Noise ◽  
Natural Images ◽  
Training Data ◽  
Learning Approaches ◽  
Learning Method

Seismic field data are usually contaminated by random or complex noise, which seriously affect the quality of seismic data contaminating seismic imaging and seismic interpretation. Improving the signal-to-noise ratio (SNR) of seismic data has always been a key step in seismic data processing. Deep learning approaches have been successfully applied to suppress seismic random noise. The training examples are essential in deep learning methods, especially for the geophysical problems, where the complete training data are not easy to be acquired due to high cost of acquisition. In this work, we propose a natural images pre-trained deep learning method to suppress seismic random noise through insight of the transfer learning. Our network contains pre-trained and post-trained networks: the former is trained by natural images to obtain the preliminary denoising results, while the latter is trained by a small amount of seismic images to fine-tune the denoising effects by semi-supervised learning to enhance the continuity of geological structures. The results of four types of synthetic seismic data and six field data demonstrate that our network has great performance in seismic random noise suppression in terms of both quantitative metrics and intuitive effects.

scholarly journals Distinguishing Computer-Generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning

Sensors ◽  
2018 ◽  
Vol 18 (4) ◽  
pp. 1296 ◽  
Author(s):  
Ye Yao ◽  
Weitong Hu ◽  
Wei Zhang ◽  
Ting Wu ◽  
Yun-Qing Shi
Keyword(s):  
Deep Learning ◽  
Natural Images ◽  
Pattern Noise ◽  
Sensor Pattern Noise

Intellectual Curve Scene Text Detection from natural images using MSER descriptor based Region Segmentation approach

2019 ◽  
Vol 09 ◽  
Author(s):  
Deepak Kumar ◽  
Ramandeep SIngh
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Text Detection ◽  
Natural Images ◽  
Natural Image ◽  
Morphological Operations ◽  
Text Data ◽  
Region Detection ◽  
Scene Text Detection ◽  
Time Accuracy

A novel method to detect the text region from the natural image using the discriminative deep feature of text regions is presented with deep learning concept in this manuscript. Curve text detection (CTD) from the natural image is generally based on two different tasks: learning of text data and text region detection. In the learning of text data, the goal is to train the system with a sample of letters and natural images, while, in text region detection, the aim is to confirm the detected regions are text region or not. The emphasis of this research is on the development of deep learning algorithm. A novel approach has been proposed to detect the text region from natural images which simultaneously tackles three combined challenges: 1) pre-processing of the image without losing text region; 2) appropriate segmentation of text region using their strokes, and 3) training of data. In pre-processing, image enhancement and binarization are done then morphological operations are defined with the Maximally stable extremal region (MSER) based segmentation technique which operates on the basis of stroke region of text and then finds out the (Speed Up Robust Feature) SURF key point from those regions. Based on the SURF feature, text region is detected from the images using a trained structure of Artificial neural network (ANN) which is based on deep learning mechanism. CTW-1500 dataset is used to simulate the proposed work and the parameters like Precision, Recall, F-Measure (H-mean), Execution time, Accuracy and Error Rate are computed and are compared with the existing work to depict the effectiveness of the work.

scholarly journals Fully automatic wound segmentation with deep convolutional neural networks

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Chuanbo Wang ◽  
D. M. Anisuzzaman ◽  
Victor Williamson ◽  
Mrinal Kanti Dhar ◽  
Behrouz Rostami ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Chronic Wounds ◽  
Wound Care ◽  
Natural Images ◽  
Wound Management ◽  
Learning Models ◽  
Deep Convolutional Neural Networks ◽  
Care Protocol ◽  
Fully Automatic

AbstractAcute and chronic wounds have varying etiologies and are an economic burden to healthcare systems around the world. The advanced wound care market is expected to exceed $22 billion by 2024. Wound care professionals rely heavily on images and image documentation for proper diagnosis and treatment. Unfortunately lack of expertise can lead to improper diagnosis of wound etiology and inaccurate wound management and documentation. Fully automatic segmentation of wound areas in natural images is an important part of the diagnosis and care protocol since it is crucial to measure the area of the wound and provide quantitative parameters in the treatment. Various deep learning models have gained success in image analysis including semantic segmentation. This manuscript proposes a novel convolutional framework based on MobileNetV2 and connected component labelling to segment wound regions from natural images. The advantage of this model is its lightweight and less compute-intensive architecture. The performance is not compromised and is comparable to deeper neural networks. We build an annotated wound image dataset consisting of 1109 foot ulcer images from 889 patients to train and test the deep learning models. We demonstrate the effectiveness and mobility of our method by conducting comprehensive experiments and analyses on various segmentation neural networks. The full implementation is available at https://github.com/uwm-bigdata/wound-segmentation.

scholarly journals A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds

2019 ◽  
Vol 11 (7) ◽  
pp. 765 ◽  
Author(s):  
Yuanyuan Wang ◽  
Chao Wang ◽  
Hong Zhang ◽  
Yingbo Dong ◽  
Sisi Wei
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Natural Images ◽  
Average Precision ◽  
Sar Images ◽  
Test Dataset ◽  
Ship Detection ◽  
Art Object ◽  
Public Dataset ◽  
Sar Imagery

With the launch of space-borne satellites, more synthetic aperture radar (SAR) images are available than ever before, thus making dynamic ship monitoring possible. Object detectors in deep learning achieve top performance, benefitting from a free public dataset. Unfortunately, due to the lack of a large volume of labeled datasets, object detectors for SAR ship detection have developed slowly. To boost the development of object detectors in SAR images, a SAR dataset is constructed. This dataset labeled by SAR experts was created using 102 Chinese Gaofen-3 images and 108 Sentinel-1 images. It consists of 43,819 ship chips of 256 pixels in both range and azimuth. These ships mainly have distinct scales and backgrounds. Moreover, modified state-of-the-art object detectors from natural images are trained and can be used as baselines. Experimental results reveal that object detectors achieve higher mean average precision (mAP) on the test dataset and have high generalization performance on new SAR imagery without land-ocean segmentation, demonstrating the benefits of the dataset we constructed.

Sign in / Sign up

Export Citation Format

Share Document