Comment on using the uniformity measure for performance measure in image segmentation

Ng, Wan Sing; Lee, C.K.

doi:10.1109/34.537347

Cited by 23 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ng and Lee [7] proved that the optimality of uniformity measure is basically equivalent to the criterion measure proposed by Otsu [8]. Herein, the uniformity measure (UM) adopted from Ng and Lee [7] is defined as:…”

Section: Motion Blurred Detectionmentioning

confidence: 99%

“…In [7], the uniformity of a feature over a region is defined as being inversely proportional to the variance of the values of that feature, evaluated at every pixel belonging to that region, with an appropriate weighting factor. Ng and Lee [7] proved that the optimality of uniformity measure is basically equivalent to the criterion measure proposed by Otsu [8]. Herein, the uniformity measure (UM) adopted from Ng and Lee [7] is defined as:…”

Section: Motion Blurred Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Video Stitching System of Heterogeneous Car Video Recorders

Tseng

Tsai

2015

Current Approaches in Applied Artificial Intelligence

View full text Add to dashboard Cite

Abstract. Many heterogeneous car video recorders are sold in the market. In order to record the ultra-wide-angle road scenes, at least two heterogeneous recorders are used. These heterogeneous recorders have different viewing angles, different resolutions, and different lens sensors. Because of different hardware and software of the heterogeneous recorders, the captured videos are heterogeneous, which is very challenging for video stitching research. The traditional image stitching system includes color correction, feature detection, feature descriptor, feature matching, and video stitching. When a traditional image stitching system is used to process the images captured by homogeneous cameras, the results are reasonably good. However, when a traditional image stitching system is used to process the images captured by heterogeneous cameras, the results are not so good. Furthermore, applying a traditional image stitching system to process videos captured by heterogeneous car video recorders is timeconsuming. This paper presents a study that tested multiple existing methods to evaluate their capability when used to stitch heterogeneous images to allow a driver to see an ultra-wide-angle driving view without blind spots and to record these images. Experimental results show that some methods used in this study can be used for this purpose, but they have significant error rates and are timeconsuming.

show abstract

Section: Motion Blurred Detectionmentioning

confidence: 99%

Section: Motion Blurred Detectionmentioning

confidence: 99%

Video Stitching System of Heterogeneous Car Video Recorders

Tseng

Tsai

2015

Current Approaches in Applied Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Table 1 lists some histogram-based algorithms, including (1) variance-based methods, such as Otsu's method and its refinements [19,20]; (2) iterative selection schemes, including the method of [21][22][23]; (3) moment-based methods, such as the method of Tsai [24]; (4) entropic thresholding, including Pun [25,26], and its refinement [27][28][29][30][31][32]; and (5) minimum-error methods, such as Kittler and Illingworth [33] and Pal and Bhandari [34]. Moreover, the features of images may provide clues for appropriately selecting the thresholding value.…”

Section: Use Of Thresholding Algorithmmentioning

confidence: 99%

Bilevel thresholding of floc images

Chu

Lee

Tay

2004

Journal of Colloid and Interface Science

View full text Add to dashboard Cite

“…It is evaluated at every pixel belonging to that region with an appropriate weighting factor. Ng and Lee [8] proved that the optimality of uniformity measure is basically equivalent to the criterion measure proposed by Otsu [9]. Herein, the uniformity measure (UM) adopted from Ng and Lee [8] is defined as: uniformity measure for a given threshold value.…”

Section: �>� Wmentioning

confidence: 99%

Non-motion blur detection for helping blind persons to “see” business cards

Tsai¹

2012

2012 International Conference on Machine Learning and Cybernetics

View full text Add to dashboard Cite

The conventional methods to help visually impaired persons to read the text, menus, and book covers in natural scene have many problems. They assumed that the blind persons are standing still and the captured scene is non-moving.Moreover, the blind persons has difficulty to determine that the menu or the book cover is captured by the camera. Furthermore, these methods can not "see" business cards to help the blind persons. In this work, a non-motion blur detection system is proposed for helping blind persons to "see" business cards. The proposed method includes moving object detection, thumb detection, and non-motion blur detection methods.Experimental results show that the performance of the proposed method is better than conventional two frame differencing method. Furthermore, the proposed method reduces the time complexity and avoids the blind persons to hear a synthesized voice repeating from the same text.

show abstract

Comment on using the uniformity measure for performance measure in image segmentation

Cited by 23 publications

References 6 publications

Video Stitching System of Heterogeneous Car Video Recorders

Video Stitching System of Heterogeneous Car Video Recorders

Bilevel thresholding of floc images

Non-motion blur detection for helping blind persons to “see” business cards

Contact Info

Product

Resources

About

Comment on using the uniformity measure for performance measure in image segmentation

Cited by 23 publications

References 6 publications

Video Stitching System of Heterogeneous Car Video Recorders

Video Stitching System of Heterogeneous Car Video Recorders

Bilevel thresholding of floc images

Non-motion blur detection for helping blind persons to &#x201C;see&#x201D; business cards

Contact Info

Product

Resources

About

Non-motion blur detection for helping blind persons to “see” business cards