Automatic estimation and segmentation of partial blur in natural images

Javaran, Taiebeh Askari; Hassanpour, Hamid; Abolghasemi, Vahid

doi:10.1007/s00371-015-1166-z

Cited by 22 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results yielded by the proposed approach eliminated noisy background and have closer resemblance to the ground-truth images, compared to previously published research. The segmented results produced by Su et al [10], Shi et al [13], and Javaran et al [17] have mixed-up the sharp and blurred regions and the objects are not noticeable in the results. Henceforth, the proposed approach, prominently detected the sharp objects from the blurred background as compared to referenced schemes.…”

Section: A Evaluation and Parameter Selectionmentioning

confidence: 91%

“…Our approach outperformed the nine classical techniques [10,13,17,14,22,25,27,24,32] in terms of the error-control and the accurate focused region location. Tang et al [25] missed the details of the targeted objects.…”

Section: A Evaluation and Parameter Selectionmentioning

confidence: 92%

“…Vu et al [16] estimated the amplitude-spectrum slop and the complete spatial-variation for each block of the defocused image. Javaran et al [17] designed the principles about high frequency information that remains same in re-blurred image and is used for out-of-focused region detection. Golestaneh et al [18] developed a High Frequency multi-scale Fusion Sort-Transform (HiFST) of gradient magnitudes in the detection of out of focused regions.…”

Section: Literature Review Presentlymentioning

confidence: 99%

“…Shi et al [43], and Zhao et al [46], were 136.407s and 33.139s, respectively. The results of the proposed approach were compared with those of nine other comparators [10,13,17,14,22,25,27,24,32]. Some of the schemes among them are edge-based techniques i.e., Tang et al [22], Karaali and Jung [24], Tang et al [25], and Xu et al [27], while the rest are recent pixelbased techniques.…”

Section: A Evaluation and Parameter Selectionmentioning

confidence: 99%

“…Shi et al [13] applied a multi scale inference structure following the Naïve Bayes classifier. Javaran et al [17] adopted DCT-based feature vector for blur map extraction and segmented the images into blurred and sharp regions. Tang et al [25] used a log averagedspectrum residual mechanism for segmenting the focused-smooth region and blurred-smooth region in defocus and motion-blurred images.…”

Section: A Evaluation and Parameter Selectionmentioning

confidence: 99%

See 4 more Smart Citations

A Novel Defocus-Blur Region Detection Approach Based on DCT Feature and PCNN Structure

Basar,

Ali,

Waheed

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The motion or out-of-focus effect in digital images is the main reason for the blurred regions in defocused-blurred images. It may adversely affect various image features such as texture, pixel, and region. Therefore, it is important to detect in-focused objects in defocused-blurred images after the segmentation of blurred and non-blurred regions. The state-of-the-art techniques are prone to noisy pixels, and their local descriptors for developing segmentation metrics are also complex. To address these issues, this research, therefore, proposed a novel and hybrid focused detection approach based on Discrete Cosine Transform (DCT) coefficients and PC Neural Net (PCNN) structure. The proposed approach partially resolves the limitations of the existing contrast schemes to detect focused smooth objects from the outof-focused smooth regions in the defocus dataset. The visual and quantitative evaluation illustrates that the proposed approach outperformed in terms of accuracy and efficiency to referenced algorithms. The highest ℱ 𝛼 -score of the proposed approach on Zhao's dataset is 0.7940 whereas on Shi's dataset is 0.9178.

show abstract

Section: A Evaluation and Parameter Selectionmentioning

confidence: 91%