Perspective Image Rectification Based on Improved Hough Transformation and Perspective Transformation

The slump flow and flow time T200 are the main parameters to evaluate the rheological properties of cement paste. Generally, the manual measurement method is used and it is difficult to get T200 accurately. In this paper, an automatic measurement method of slump flow based on dynamic image processing technology is studied. Firstly, the cement paste flowability test video is divided into frames every 100 ms; secondly, based on the principle of perspective transformation, an automatic point selection method is proposed to correct the frame image to solve the problem of shooting angle; thirdly, the watershed algorithm based on distance transformation is used to segment the boundary of the cement paste area, and the slump flow is calculated according to the polar coordinates of the boundary; lastly, the relationship curve between slump flow and time is automatically output, and the slump flow at any time is obtained. The method is verified by nine groups of cement paste flowability tests. The results show that this method can fastly and accurately obtain the slump flow and flow time T200. Compared with the traditional manual measurement method, the measurement error of slump flow is less than 2%, and the measurement error of flow time T200 is less than 8%. The method enables real-time dynamic measurement of the slump flow.

show abstract

“…In this paper, the perspective transformation [11] method is used to correct the glass plate, as shown in…”

Section: Methods Of Image Correction Automaticallymentioning

confidence: 99%

Automatic Measurement Method of Slump Flow of Cement Paste Based on Dynamic Image Processing Technology

Gao

Wang

et al. 2022

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Hough transform is often used for image tilt correction, but when the degree of image distortion is serious, the effect of directly using the Hough transform method is not ideal. To this end, the paper [14] proposes an improved Hough transform image correction method combined with perspective transformation technology.…”

Section: Posture Correctionmentioning

confidence: 99%

Multiform stamp image pose correction algorithm based on perspective transformation

Yin

Pan

Yin

2023

International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023)

View full text Add to dashboard Cite

The combination of perspective transformation technology and Hough transformation can achieve good image correction effect. In the application process, in order to determine the perspective transformation parameters, for the rectangular seal, the four vertices of the seal can be selected as the reference points of the transformation. However, the above method can not be directly applied to oval and circular seals. Therefore, this paper puts forward a simple and effective solution. Firstly, the minimum circumscribed frames of circular and elliptical seals are made respectively, and the vertex position coordinates are calculated. Using the constructed external frame, the above problem is transformed into the correction of a rectangular or square image, so that the perspective transformation technology can be extended to the correction of other shapes such as ellipse and circle. At the same time, BM3D filtering is used to reduce the impact of noise. In the basic estimation, K-means clustering is used to search the matching block in the neighborhood of the reference block, and the generated weight matrix is used to improve the matching degree of the module and the accuracy of subsequent aggregation. The preliminary experimental results show that the idea proposed in this paper is simple and effective, and can realize the unified correction of seal image posture of different shapes.

show abstract

“…In the traditional sense of target recognition, mostly to extract the characteristics, which is often said that the points and lines, and then through some means, such as translation, rotation and transformation [3], the result is another image that is the most close to the target image, then evaluate the result with similarity. As the examination room is a special indoor environment, the position of the camera in it is settled, so it has many characteristics such as background image is single and does not change over the time, so the background subtraction [4] is used to identify the target that is very effective, this paper also through the normalized template matching [5,6] to identify the examinee regions, so can realize the real-time statistics number in the examination room and greatly improve the identification accuracy.…”

Section: Introductionmentioning

confidence: 99%

The Improvement and Implementation of Examinee Identification Algorithm Based on the Video Surveillance

Liu

et al. 2014

AMM

View full text Add to dashboard Cite

Making the video invigilation more easy is a hot topic in the research of intelligent monitoring system. This paper proposes the examinee identification algorithm based on the video surveillance. Firstly, transform the video frame to the orthograph by using perspective transformation, extract the desks template, and get the place of desk according to template matching, then get the place of examinee. Comparing the image about no people included and people included will detect whether examinee in his place by using the comprehensive method which is background subtraction and the normalized matching algorithm, so can statistical number of examinees. Experimental results show that this method is simple, has a good real-time performance and robustness.

show abstract

Perspective Image Rectification Based on Improved Hough Transformation and Perspective Transformation

Cited by 13 publications

References 0 publications

Automatic Measurement Method of Slump Flow of Cement Paste Based on Dynamic Image Processing Technology

Automatic Measurement Method of Slump Flow of Cement Paste Based on Dynamic Image Processing Technology

Multiform stamp image pose correction algorithm based on perspective transformation

The Improvement and Implementation of Examinee Identification Algorithm Based on the Video Surveillance

Contact Info

Product

Resources

About