Image retrieval based on texture using latent space representation of discrete Fourier transformed maps

Saikia, Surajit; Fernández-Robles, Laura; Alegre, Enrique; Fidalgo, Eduardo

doi:10.1007/s00521-021-05955-2

Cited by 8 publications

(4 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The statistical method mainly describes texture features by analyzing the grayscale distribution in images, like gray level co-occurrence matrix [7], scale-invariant feature transform (SIFT) [8], and local binary pattern (LBP) [9]. The frequency method converts the grayscale distribution in the spatial domain into the frequency distribution in the frequency domain to describe texture features, mainly including wavelet transform [10] and Fourier transform [11]. The model method uses a small number of parameters to establish a mathematical model to describe texture features, like Markov models [12], and fractal dimensions [13].…”

Section: Texture Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A novel plaid fabric image retrieval method based on hand- crafted features

Zhang,

Zhao,

Ruru

et al. 2024

Preprint

View full text Add to dashboard Cite

Fabric image retrieval can obtain technological parameters of existing similar fabric images to guide production, saving lots of labor and material resources in the proofing process. This paper presents a novel image retrieval method for plaid fabrics based on hand-crafted features. First, local texture descriptors are extracted by the local binary pattern on the separated images which are processed by Fourier transform. Global texture descriptors are extracted by Scale-Invariant Feature Transform (SIFT) and Vector of Locally Aggregated Descriptors (VLAD). Second, color moments with image partitioning are extracted to characterize spatial color information of plaid fabric images. Third, the similarities of the three features are calculated and fused by the weight assignment to realize the plaid fabric image retrieval. To verify the proposed method, over 30,000 plaid fabric samples are collected from the factory to build the image database as the benchmark. Experiments show that precision and recall at rank five reach 70.6% and 62.6%, respectively, and mAP reaches 0.690. Results prove that the proposed method is feasible and effective, which can provide references for the worker and help the fabric manufacturing factory save lots of labor and material resources.

show abstract

Section: Texture Featuresmentioning

confidence: 99%

“…Then, a similarityweighted approach is used to fuse the texture features and color features. Assuming that ρ1, ρ2, and ρ3 represent the local texture feature, global texture feature, and color feature, respectively, the final similarity S can be defined by Equation (11).…”

Section: Similarity Measurementmentioning

confidence: 99%

A novel plaid fabric image retrieval method based on hand- crafted features

Zhang,

Zhao,

Ruru

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Any periodic signal satisfying Dirichlet condition can be expressed as infinite series of complex harmonic signal; and for aperiodic signal x ( t ) , if it meets the requirements of energy limited signal and Dirichlet condition, it can be Fourier transformed. 22,23 This signal can be regarded as a linear combination of infinite sinusoidal functions with different frequencies and different initial phases; its amplitude is the value of the corresponding frequency | X ( j 2 π f ) | , and its phase is the value of the corresponding frequency φ ( 2 π f ) :…”

Section: Load Solving Theorymentioning

confidence: 99%

Study on contactless measurement method of dropper load

Liu

Liang

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The fatigue fracture of dropper will threaten the safe operation of high-speed railway. The accurate measurement of dropper load plays an important role in dropper fatigue test and service life prediction. In this work, according to the structural characteristics of catenary suspension and based on string vibration theory, a contactless method for measuring dropper load is proposed. In this method, the edge recognition technology is used to obtain the vibration displacement time history data of the dropper clamp position on the messenger wire, the random vibration is transformed into the linear superposition of sinusoidal vibration through Fourier transform to solve the vibration differential equation. Through the relationship between the shape change of messenger wire and concentrated force, the change of dropper load is analyzed. The measurement accuracy is tested on the test platform built in the laboratory, and the results show the measurement accuracy can reach 0.50%.

show abstract

“…However, to evaluate the processing information, the relevant sensitive features of the surface need to be accurately identified and extracted. Saikia et al [16] introduce a method with image Fourier transform [17] for extracting characteristics of filter frequency changes during processing. Based on Empirical Modal Decomposition (EMD) [18,19], Sun Huibin et al [20] proposed a texture monitoring method, successfully extracting sensitive features from vibration signals on the basis of empirical model decomposition, and then establishing a mapping relationship from texture feature to texture image features and vibration signal feature.…”

Section: Introductionmentioning

confidence: 99%

Texture feature similarity-based roughness intelligent evaluation: a case study applied to milled surfaces

Man,

Zhou,

Sun

et al. 2024

Surf. Topogr.: Metrol. Prop.

View full text Add to dashboard Cite

Surface roughness is of great significance in maintaining mechanical performance and improving the reliability of the equipment. However, fast surface roughness evaluations that are sufficiently stable and efficient for engineering in-situ use have not yet been realized. To address this issue, an image-driven roughness intelligent method is proposed in this research. By evaluating the texture similarity intelligently between the testing image and the reference image, the surface roughness of the testing image can be acquired. Firstly, with a proposed adaptive texture extraction method, the texture feature of an image can be extracted even under a complex background. Secondly, by establishing the graph structure of the texture grayscale features, the similarity between different images is evaluated. Finally, by establishing a sparrow-optimized support vector machine regression method, the mapping relationship between the similarity and the surface roughness can be acquired. The experimental results indicate that the proposed method for intelligent evaluation of roughness has superior prediction performance (the average relative prediction error of Ra and Rz are 8.8156% and 8.0571%, respectively). Therefore, this work provides a useful tool for non-contact detection of workpiece surface roughness.

show abstract

Image retrieval based on texture using latent space representation of discrete Fourier transformed maps

Cited by 8 publications

References 64 publications

A novel plaid fabric image retrieval method based on hand- crafted features

A novel plaid fabric image retrieval method based on hand- crafted features

Study on contactless measurement method of dropper load

Texture feature similarity-based roughness intelligent evaluation: a case study applied to milled surfaces

Contact Info

Product

Resources

About