scholarly journals Research on Clothing Image Database Retrieval Algorithm Based on Wavelet Transform

2022 ◽  
Vol 2022 ◽  
pp. 1-8
Author(s):  
Xiaoyue Cui
Keyword(s):  
Wavelet Transform ◽  
Image Data ◽  
Data Retrieval ◽  
Image Database ◽  
Fair Value ◽  
Visual Features ◽  
Retrieval Algorithm ◽  
Wavelet Filter ◽  
Database Retrieval ◽  
Retrieval Accuracy

Aiming at the problems of low image data retrieval accuracy and slow retrieval speed in the existing image database retrieval algorithms, this paper designs a clothing image database retrieval algorithm based on wavelet transform. Firstly, it represents the color consistency vector of clothing image, reflects the composition and distribution of image color through color histogram, quantifies the visual features of clothing image, aggregates them into a fixed size representation vector, and uses the Fair Value (FV) model to complete the collection of clothing image data. Then, the size of the clothing image is adjusted by using the size transformation technology, and the clothing pattern is divided into four moments with the same size. On this basis, the clothing image is discretized with the help of Hu invariant moment to complete the preprocessing of clothing image data. Finally, the generating function of wavelet transform is determined, and a cluster of functions is obtained through translation and expansion. The wavelet filter is decomposed into basic modules, and then, the wavelet transform is studied step by step. The clothing image data are regarded as a signal, split, predicted, and updated and input into the wavelet model, and the retrieval research of clothing image database is completed. The experimental results show that the design of the retrieval algorithm is reasonable, the retrieval data accuracy is high, and the retrieval speed is fast.

Image database retrieval utilizing affinity relationships

2003 ◽  
Author(s):  
Mei-Ling Shyu ◽  
Shu-Ching Chen ◽  
Min Chen ◽  
Chengcui Zhang ◽  
Kanoksri Sarinnapakorn
Keyword(s):  
Image Database ◽  
Database Retrieval

scholarly journals Identifying Habitat Elements from Bird Images Using Deep Convolutional Neural Networks

Animals ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 1263
Author(s):  
Zhaojun Wang ◽  
Jiangning Wang ◽  
Congtian Lin ◽  
Yan Han ◽  
Zhaosheng Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Digital Technology ◽  
Rapid Development ◽  
Image Data ◽  
Image Database ◽  
Test Accuracy ◽  
Practical Application ◽  
Accuracy Rate ◽  
Deep Convolutional Neural Networks

With the rapid development of digital technology, bird images have become an important part of ornithology research data. However, due to the rapid growth of bird image data, it has become a major challenge to effectively process such a large amount of data. In recent years, deep convolutional neural networks (DCNNs) have shown great potential and effectiveness in a variety of tasks regarding the automatic processing of bird images. However, no research has been conducted on the recognition of habitat elements in bird images, which is of great help when extracting habitat information from bird images. Here, we demonstrate the recognition of habitat elements using four DCNN models trained end-to-end directly based on images. To carry out this research, an image database called Habitat Elements of Bird Images (HEOBs-10) and composed of 10 categories of habitat elements was built, making future benchmarks and evaluations possible. Experiments showed that good results can be obtained by all the tested models. ResNet-152-based models yielded the best test accuracy rate (95.52%); the AlexNet-based model yielded the lowest test accuracy rate (89.48%). We conclude that DCNNs could be efficient and useful for automatically identifying habitat elements from bird images, and we believe that the practical application of this technology will be helpful for studying the relationships between birds and habitat elements.

Tangent height registration method for the Version 14 data retrieval algorithm of the solar occultation sensor ILAS-II

2007 ◽  
Vol 46 (29) ◽  
pp. 7196 ◽  
Author(s):  
Tomoaki Tanaka ◽  
Hideaki Nakajima ◽  
Takafumi Sugita ◽  
Mitsumu K. Ejiri ◽  
Hitoshi Irie ◽  
...  
Keyword(s):  
Data Retrieval ◽  
Retrieval Algorithm ◽  
Registration Method ◽  
Solar Occultation

Researches on the Object-Oriented Model of Distributed Image Database

2014 ◽  
Vol 543-547 ◽  
pp. 2184-2187
Author(s):  
Ping Zhang Gou ◽  
Yong Zhong Tang
Keyword(s):  
Comparative Analysis ◽  
Data Model ◽  
Object Oriented ◽  
Image Data ◽  
Image Database ◽  
Management Modes

Combined with the characteristics of the image data, this study contrasted four kinds of data model. Then it analyzed the three kinds of realization methods of image database, comparative analysis of management modes of the distributed image database finally.

Non-Subsampled Contourlet Texture Retrieval Using Four Estimators

2012 ◽  
Vol 263-266 ◽  
pp. 167-170 ◽  
Author(s):  
Xin Wu Chen ◽  
Jing Ge ◽  
Jin Gen Liu
Keyword(s):  
Wavelet Transform ◽  
Standard Deviation ◽  
Digital Images ◽  
Contourlet Transform ◽  
Retrieval Algorithm ◽  
Retrieval Rate ◽  
Retrieval Systems ◽  
Texture Information ◽  
Shift Invariance ◽  
Texture Retrieval

Contourlet transform is superior to wavelet transform in representing texture information and sparser in describing geometric structures in digital images, but lack of robust character of shift invariance. Non-subsampled contourlet transform (NSCT) alleviates this shortcoming hence more suitable for texture and has been studied for image de-noising, enhancement, and retrieval situations. Focus on improving the retrieval rates of existing contourlet transforms retrieval systems, a new texture retrieval algorithm was proposed. In the algorithm, texture information was represented by four statistical estimators, namely, L2-energy, kurtosis, standard deviation and L1-energy of each sub-band coefficients in NSCT domain. Experimental results show that the new algorithm can make a higher retrieval rate than the combination of standard deviation and energy which is most commonly used today.

scholarly journals Comparison of the cloud top heights retrieved from MODIS and AHI satellite data with ground-based Ka-band radar

2019 ◽  
Author(s):  
Juan Huo ◽  
Daren Lu ◽  
Shu Duan ◽  
Yongheng Bi ◽  
Bo Liu
Keyword(s):  
Satellite Data ◽  
Radar Data ◽  
Retrieval Algorithm ◽  
Ka Band ◽  
Retrieval Accuracy ◽  
Retrieval Algorithms ◽  
Moderate Resolution ◽  
Resolution Imaging ◽  
Radar Measurements ◽  
Moderate Resolution Imaging Spectroradiometer

Abstract. To better understand the accuracy of cloud top heights (CTHs) derived from passive satellite data, ground-based Ka-band radar measurements from 2016 and 2017 in Beijing were compared with CTH data inferred from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Advanced Himawari Imager (AHI). Relative to the radar CTHs, the MODIS CTHs were found to be underestimated by −1.10 ± 2.53 km and 49 % of CTH differences were within 1.0 km. Like the MODIS results, the AHI CTHs were underestimated by −1.10 ± 2.27 km and 42 % were within 1.0 km. Both the MODIS and AHI retrieval accuracy depended strongly on the cloud depth (CD). Large differences were mainly occurring for the retrieval of thin clouds of CD  1 km, the CTH difference decreased to −0.48 ± 1.70 km for MODIS and to −0.76 ± 1.63 km for AHI. MODIS CTHs greater than 6 km showed better agreement with the radar data than those less than 4 km. Statistical analysis showed that the average AHI CTHs were lower than the average MODIS CTHs by −0.64 ± 2.36 km. The monthly accuracy of both retrieval algorithms was studied and it was found that the AHI retrieval algorithm had the largest bias in winter while the MODIS retrieval algorithm had the lowest accuracy in spring.

Validation of TROPOMI nadir ozone profile retrievals: Methodology and first results

2021 ◽  
Author(s):  
Arno Keppens ◽  
Jean-Christopher Lambert ◽  
Daan Hubert ◽  
Steven Compernolle ◽  
Tijl Verhoelst ◽  
...  
Keyword(s):  
Near Infrared ◽  
Stratospheric Ozone ◽  
Estimation Method ◽  
Optimal Estimation ◽  
Data Retrieval ◽  
Atmospheric Composition ◽  
Retrieval Algorithm ◽  
Validation Data ◽  
Ozone Profile ◽  
Early Afternoon

<p>Part of the space segment of EU’s Copernicus Earth Observation programme, the Sentinel-5 Precursor (S5P) mission is dedicated to global and European atmospheric composition measurements of air quality, climate and the stratospheric ozone layer. On board of the S5P early afternoon polar satellite, the imaging spectrometer TROPOMI (TROPOspheric Monitoring Instrument) performs nadir measurements of the Earth radiance within the UV-visible and near-infrared spectral ranges, from which atmospheric ozone profile data are retrieved. Developed at the Royal Netherlands Meteorological Institute (KNMI) and based on the optimal estimation method, TROPOMI’s operational ozone profile retrieval algorithm has recently been upgraded. With respect to early retrieval attempts, accuracy is expected to have improved significantly, also thanks to recent updates of the TROPOMI Level-1b data product. This work reports on the initial validation of the improved TROPOMI height-resolved ozone data in the troposphere and stratosphere, as collected both from the operational S5P Mission Performance Centre/Validation Data Analysis Facility (MPC/VDAF) and from the S5PVT scientific project CHEOPS-5p. Based on the same validation best practices as developed for and applied to heritage sensors like GOME-2, OMI and IASI (Keppens et al., 2015, 2018), the validation methodology relies on the analysis of data retrieval diagnostics – like the averaging kernels’ information content – and on comparisons of TROPOMI data with reference ozone profile measurements. The latter are acquired by ozonesonde, stratospheric lidar, and tropospheric lidar stations performing network operation in the context of WMO's Global Atmosphere Watch and its contributing networks NDACC and SHADOZ. The dependence of TROPOMI’s ozone profile uncertainty on several influence quantities like cloud fraction and measurement parameters like sun and scan angles is examined and discussed. This work concludes with a set of quality indicators, enabling users to verify the fitness-for-purpose of the S5P data.</p>

Sign in / Sign up

Export Citation Format

Share Document