Modified Scale-Space Analysis in Frequency Domain Based on Adaptive Multiscale Gaussian Filter for Saliency Detection

Jaemsiri, Jenjira; Titijaroonroj, Taravichet; Rungrattanaubol, Jaratsri

doi:10.1109/jcsse.2019.8864211

Cited by 3 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A pixel resolution of this dataset is 175×176. The proposed method is compared the effectiveness against the ability of five state-of-the-art methods, namely Itti [11], SUN [1], SR [12], SAL [2], HFT [13], MSS [16], IASSS [17], EHOLA [18], and USS [19]. Those methods are implemented as baselines.…”

Section: Testing With Psychological Pattern Imagesmentioning

confidence: 99%

“…Those methods are implemented as baselines. For fairness of comparison, the parameter setting of the baseline algorithms is based on their recommendation in [1,2,[11][12][13][16][17][18][19]. On the other hand, the parameters of the proposed method are defined by the structural feature in each object as shown in Eqs.…”

Section: Testing With Psychological Pattern Imagesmentioning

confidence: 99%

“…The first two experiments tested with psychological pattern images and Thai text images in natural scenes. The experimental results show that the proposed method achieves success in the empirical response to the psychological pattern images and in predicting the text areas as well when compared with the state-of-the-art methods [1,2,[11][12][13][16][17][18][19]. The last experiment evaluated the computational time.…”

Section: Introductionmentioning

confidence: 99%

“…This method can predict human fixation more accurately, but some failures still occur, as reported in [13], because this approach only uses the low-level features in the frequency domain. After that, the modified spectrum scale space [16], which is extended from Li's method based on the adaptive multiscale Gaussian filter, was presented in 2019 to suppress the Fourier spectrum of the non-saliency region. Thus far, most papers have used either spatial-domain features [1,11] or frequency-domain features [2,12,13,[16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

“…After that, the modified spectrum scale space [16], which is extended from Li's method based on the adaptive multiscale Gaussian filter, was presented in 2019 to suppress the Fourier spectrum of the non-saliency region. Thus far, most papers have used either spatial-domain features [1,11] or frequency-domain features [2,12,13,[16][17][18][19]. However, the use of only one domain feature is insufficient to improve the detection efficiency.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Spatial-Frequency Redistribution-based Saliency Region Detection for Thai Text Localisation

Titijaroonroj

Suttapakti

Nunsong

2022

ECTI-CIT Transactions

Self Cite

View full text Add to dashboard Cite

Saliency region detection plays an important role in computer vision applications and related areas, such as human fixation, figure-ground separation, face detection, and image compression. Nevertheless, state-of-the-art methods can moderately detect the saliency regions of a psychological pattern dataset. Therefore, this paper proposes a spatial-frequency redistribution (SFR) method to improve the efficiency of the detection of the saliency regions. The proposed SFR method consists of two main procedures: (i) adaptive cosine image construction-and-implantation and (ii) saliency region detection using complete multiple-object-implanted images. The former procedure constructs an adaptive cosine image by using a cosine function based on an object structure and then individually implants it into each object detectable. This stage provides the first significant property, spatial redistribution, to the object implanted. The adaptive cosine image redistributes the objects for controllability. Then, the latter procedure transforms a complete multiple object-implanted image into the frequency domain. At this point, the second significant property, frequency redistribution, provides the simple technique for identifying and separating the target object from the unwanted objects and background. In this paper, these properties are referred to as spatial-frequency redistribution. This method was realized as a computer program, and then such program was tested with a psychological pattern dataset and a Thai text dataset. The experimental results, when compared with state-of-the-art methods, show that the proposed SFR method can achieve the clear detection of the attention region in the psychological pattern dataset. Moreover, the proposed method can achieve a F-value of 80.28% with a recall and precision of 76.32% and 85.23%, respectively, for Thai text localisation in the Thai text dataset.

show abstract

Section: Testing With Psychological Pattern Imagesmentioning

confidence: 99%

Section: Testing With Psychological Pattern Imagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Spatial-Frequency Redistribution-based Saliency Region Detection for Thai Text Localisation

Titijaroonroj

Suttapakti

Nunsong

2022

ECTI-CIT Transactions

Self Cite

View full text Add to dashboard Cite

show abstract

Improved Adaptive Spectrum Scale-Space in Frequency Domain for Saliency Detection

Titijaroonroj

Jaemsiri

Rungrattanaubol

2020

2020 12th International Conference on Knowledge and Smart Technology (KST)

View full text Add to dashboard Cite

Application of Discrete and Fast Fourier Transforms to Increase the Speed of Multiscale Image Analysis

Ďuriš,

Semenov,

Chumarov

2024

TEM Journal

View full text Add to dashboard Cite

The paper compares the accuracy of reconstruction using different wavelets, and the authors also use fast and discrete Fourier transforms together to calculate the forward and inverse continuous wavelet transform in the frequency domain. Due to the use of calculations in the frequency domain, it becomes possible to perform decomposition, reconstruction, image filtering, and other transformations with high performance and precision. For multiscale signal analysis, a wavelet with a rectangular amplitude-frequency response has been constructed, which allows for an increase in the accuracy of decomposition and reconstruction compared to the Mallat algorithm presented in Matlab computer mathematics. At the same time, the time of multiscale analysis is reduced several times compared to the Mallat algorithm.

show abstract

Modified Scale-Space Analysis in Frequency Domain Based on Adaptive Multiscale Gaussian Filter for Saliency Detection

Cited by 3 publications

References 6 publications

Spatial-Frequency Redistribution-based Saliency Region Detection for Thai Text Localisation

Spatial-Frequency Redistribution-based Saliency Region Detection for Thai Text Localisation

Improved Adaptive Spectrum Scale-Space in Frequency Domain for Saliency Detection

Application of Discrete and Fast Fourier Transforms to Increase the Speed of Multiscale Image Analysis

Contact Info

Product

Resources

About