Local Patch Vectors Encoded by Fisher Vectors for Image Classification

Chen, Shuangshuang; Liu, Huiyi; Zeng, Xin; Qian, Subin; Wei, Wei; Wu, Guomin; Duan, Baoyan

doi:10.3390/info9020038

Cited by 7 publications

(2 citation statements)

References 31 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is an open question that must be addressed during feature extraction stage. Recent studies generally address this issue by sampling the feature points either uniformly or randomly [41,42]. For uniform sampling, local patches are sampled densely within regular sampling grids across an image with certain pixel spacing.…”

Section: Features Extraction Using Patch-based Regionsmentioning

confidence: 99%

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

Usman¹,

Hoque²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>The bag-of-words (BoW) model is one of the most popular representation methods for image classification. However, the lack of spatial information, the intra-class diversity, and the inter-class similarity among scene categories impair its performance in the remote-sensing domain. To alleviate these issues, this paper proposes to explore the spatial dependencies between different image regions and introduces patch-based discriminative learning (PBDL) for remote-sensing scene classification. Particularly, the proposed method employs multi-level feature learning based on small, medium, and large neighborhood regions to enhance the discriminative power of image representation. To achieve this, image patches are selected through a fixed-size sliding window and sampling redundancy, a novel concept, is developed to minimize the redundant features while sustaining the relevant features for the model. Apart from multi-level learning, we explicitly impose image pyramids to magnify the visual information of the scene images and optimize their position and scale parameters locally. Motivated by this, a local descriptor is exploited to extract multi-level and multi-scale features that we represent in terms of codewords histogram by performing k-means clustering. Finally, a simple fusion strategy is proposed to balance the contribution of individual features, and the fused features are incorporated into a Bidirectional Long Short-Term Memory (BiLSTM) network for classification. Experimental results on NWPU-RESISC45, AID, UC-Merced, and WHU-RS datasets demonstrate that the proposed approach not only surpasses the conventional bag-of-words approaches but also yields significantly higher classification performance than the existing state-of-the-art deep learning methods used nowadays.</p>

show abstract

Section: Features Extraction Using Patch-based Regionsmentioning

confidence: 99%

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

Usman¹,

Hoque²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In this regard, a logical solution for search work on constructing and processing images of a helical surface would be to study the accuracy at a given step discreteness when moving the camera. Another approach is to determine the nodal points that limit the search area with local discontinuities in the image brightness values that arise at the boundaries of objects [70][71][72][73][74][75].…”

Section: Introductionmentioning

confidence: 99%

New indicators and standards for measuring of the end mill's helical groove by image processing

Pivkin,

Ershov,

Grechishnikov

et al. 2023

Optical Metrology and Inspection for Industrial Applications X

View full text Add to dashboard Cite

The studies will be carried out using optical metrology methods on a Walter Helicheck inspection machine in reflected light and a number of images were stored to form a statistical sample. Established new indicators and criteria for grinding efficiency based on image processing of the helical groove of the end mill. As a result, recommendations for the selection of optical control techniques were made for the first time at the intermediate stage of technological preparation for production, in real time, and after processing. In this work, for the first time, we prove the possibility of determining the camera displacement pith distance during continuous scanning of the profile of a helical surface in a radial section, the measurement accuracy and recreating a three-dimensional model of the object. As a result of the work of the new algorithm using the Haar-wavelet with new indicators, it was established that the actual one is located inside the focal zone, which proves the possibility of applied application of the method of monitoring the shape of helical flute of end mills using computer vision. The measurement accuracy of the helical flute increased from 4 to 12% along its profile.

show abstract

Large Scale Image Retrieval and Its Challenges

Azim

Ahmed

2018

Composing Fisher Kernels From Deep Neural Models

View full text Add to dashboard Cite

Local Patch Vectors Encoded by Fisher Vectors for Image Classification

Cited by 7 publications

References 31 publications

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

New indicators and standards for measuring of the end mill's helical groove by image processing

Large Scale Image Retrieval and Its Challenges

Contact Info

Product

Resources

About