Improved image representation and sparse representation for image classification

Zheng, Shijun; Zhang, Yongjun; Liu, Wenjie; Zou, Yongjie

doi:10.1007/s10489-019-01612-3

Cited by 15 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there has been increasing interest in sparse representation of signals. Sparse representation is widely used in the computer vision and pattern recognition in various fields, including image denoising ( Sun et al., 2014 ), image classification ( Zheng et al., 2020 ), face recognition ( Liu et al., 2019 ), disease recognition ( Feng and Zhou, 2016 ), and target tracking ( Ma and Xu, 2021 ), etc. In these applications, the sparse representation method often leads to the most advanced performance.…”

Section: Experimental Methodsmentioning

confidence: 99%

Hyperspectral detection of fresh corn peeling damage using germinating sparse classification method

Chen

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Peeling damage reduces the quality of fresh corn ear and affects the purchasing decisions of consumers. Hyperspectral imaging technique has great potential to be used for detection of peeling-damaged fresh corn. However, conventional non-machine-learning methods are limited by unsatisfactory detection accuracy, and machine-learning methods rely heavily on training samples. To address this problem, the germinating sparse classification (GSC) method is proposed to detect the peeling-damaged fresh corn. The germinating strategy is developed to refine training samples, and to dynamically adjust the number of atoms to improve the performance of dictionary, furthermore, the threshold sparse recovery algorithm is proposed to realize pixel level classification. The results demonstrated that the GSC method had the best classification effect with the overall classification accuracy of the training set was 98.33%, and that of the test set was 95.00%. The GSC method also had the highest average pixel prediction accuracy of 84.51% for the entire HSI regions and 91.94% for the damaged regions. This work represents a new method for mechanical damage detection of fresh corn using hyperspectral image (HSI).

show abstract

Section: Experimental Methodsmentioning

confidence: 99%

Hyperspectral detection of fresh corn peeling damage using germinating sparse classification method

Chen

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…In addition, Li et al designed a strategy to synthesise symmetric virtual samples synthesis [35] automatically. Considering the deformability of face images, that is, face images of the same target, which may have different pixel values at the exact location, Xu et al proposed an algorithm focusing on medium-intensity pixel values to improve classification accuracy by generating virtual images [36], and Zheng et al suggested that can retain large scale information virtual image improvement algorithm [37]; flipping the original image mirror image to obtain a mirrored virtual face can also be used…”

Section: Alternative Representation Based On Virtual Imagesmentioning

confidence: 99%

“… The normalised data distribution of the first sample in the ORL face database under the original image, the representation proposed in this paper, and the representation in Ref. [37]. …”

Section: Algorithm Analysismentioning

confidence: 99%

See 1 more Smart Citation

Sparse representation scheme with enhanced medium pixel intensity for face recognition

Zhang

Wang

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample. It has been widely used in various image classification tasks. Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class‐specific information of the test sample, which is very important for classification. For deformable images such as human faces, pixels at the same location of different images of the same subject usually have different intensities. Therefore, extracting features and correctly classifying such deformable objects is very hard. Moreover, the lighting, attitude and occlusion cause more difficulty. Considering the problems and challenges listed above, a novel image representation and classification algorithm is proposed. First, the authors’ algorithm generates virtual samples by a non‐linear variation method. This method can effectively extract the low‐frequency information of space‐domain features of the original image, which is very useful for representing deformable objects. The combination of the original and virtual samples is more beneficial to improve the classification performance and robustness of the algorithm. Thereby, the authors’ algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme. The weighting coefficients in the score fusion scheme are set entirely automatically. Finally, the algorithm classifies the samples based on the final scores. The experimental results show that our method performs better classification than conventional sparse representation algorithms.

show abstract

“…In order to combat adversarial training samples [47], several approaches include the addition of noise to feature maps, and manually set a network shortcut to enhance the performance [48]. Then, Multi-Objective Genetic Algorithm (MOGA) [49], Selective Sparse Sampling Networks (S3Ns) [50], and virtual image generation [51] are proposed for the sparse object representation. Distinct from the aforementioned generalization tricks, the proposed Aggregated-Mosaic enhances the performance on the data level, without altering the architecture and feature representations.…”

Section: Data Augmentationmentioning

confidence: 99%

An Improved Aggregated-Mosaic Method for the Sparse Object Detection of Remote Sensing Imagery

Zhao

Guan

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Object detection based on remote sensing imagery has become increasingly popular over the past few years. Unlike natural images taken by humans or surveillance cameras, the scale of remote sensing images is large, which requires the training and inference procedure to be on a cutting image. However, objects appearing in remote sensing imagery are often sparsely distributed and the labels for each class are imbalanced. This results in unstable training and inference. In this paper, we analyze the training characteristics of the remote sensing images and propose the fusion of the aggregated-mosaic training method, with the assigned-stitch augmentation and auto-target-duplication. In particular, based on the ground truth and mosaic image size, the assigned-stitch augmentation enhances each training sample with an appropriate account of objects, facilitating the smooth training procedure. Hard to detect objects, or those in classes with rare samples, are randomly selected and duplicated by the auto-target-duplication, which solves the sample imbalance or classes with insufficient results. Thus, the training process is able to focus on weak classes. We employ VEDAI and NWPU VHR-10, remote sensing datasets with sparse objects, to verify the proposed method. The YOLOv5 adopts the Mosaic as the augmentation method and is one of state-of-the-art detectors, so we choose Mosaic (YOLOv5) as the baseline. Results demonstrate that our method outperforms Mosaic (YOLOv5) by 2.72% and 5.44% on 512 × 512 and 1024 × 1024 resolution imagery, respectively. Moreover, the proposed method outperforms Mosaic (YOLOv5) by 5.48% under the NWPU VHR-10 dataset.

show abstract

Improved image representation and sparse representation for image classification

Cited by 15 publications

References 35 publications

Hyperspectral detection of fresh corn peeling damage using germinating sparse classification method

Hyperspectral detection of fresh corn peeling damage using germinating sparse classification method

Sparse representation scheme with enhanced medium pixel intensity for face recognition

An Improved Aggregated-Mosaic Method for the Sparse Object Detection of Remote Sensing Imagery

Contact Info

Product

Resources

About