A novel approach of image morphing based on pixel transformation

Rahman, M.T.; Al-Amin, Md.; Bakkre, J. Bin; Chowdhury, Ahsan Raja; Bhuiyan, Md. Al-Amin

doi:10.1109/iccitechn.2007.4579398

Cited by 16 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To make pixel-by-pixel comparison possible, the image morphing in this work reshapes a pathology image according to the external contour of the THz image to match their external shapes. 17 Although this technique is often used to create a sequence of intermediate images between the source and the target, in this case, it is used only to match the pathology to the external contour of the THz image. The morphing algorithm is performed in MATLAB ® using the following five steps, which are demonstrated in (iii) Rotation: to account for differences in orientation between the THz image and pathology, the pathology mask is temporarily assigned values of 0 (outside) and 1 (inside) and is rotated in 1-deg iterations.…”

Section: Pathology Morphing and Pathology Mask Generationmentioning

confidence: 99%

“…Digitization of pathology in this work is obtained using a morphing algorithm, which enables a pixel-by-pixel comparison between the THz images and digitized pathology results. 7,17 Of classification methods used for THz imaging of fresh tissue, the use of support vector machines (SVM) and principal component analysis (PCA) reported up to 92% accuracy for breast cancer when combined. 18 The techniques used separately showed a 96% sensitivity and 87% specificity for SVM and 92% sensitivity and 87% specificity for PCA of normal versus dysplastic tissue in colon cancer imaging.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pulsed terahertz imaging of breast cancer in freshly excised murine tumors

et al. 2018

View full text Add to dashboard Cite

This paper investigates terahertz (THz) imaging and classification of freshly excised murine xenograft breast cancer tumors. These tumors are grown via injection of E0771 breast adenocarcinoma cells into the flank of mice maintained on high-fat diet. Within 1 h of excision, the tumor and adjacent tissues are imaged using a pulsed THz system in the reflection mode. The THz images are classified using a statistical Bayesian mixture model with unsupervised and supervised approaches. Correlation with digitized pathology images is conducted using classification images assigned by a modal class decision rule. The corresponding receiver operating characteristic curves are obtained based on the classification results. A total of 13 tumor samples obtained from 9 tumors are investigated. The results show good correlation of THz images with pathology results in all samples of cancer and fat tissues. For tumor samples of cancer, fat, and muscle tissues, THz images show reasonable correlation with pathology where the primary challenge lies in the overlapping dielectric properties of cancer and muscle tissues. The use of a supervised regression approach shows improvement in the classification images although not consistently in all tissue regions. Advancing THz imaging of breast tumors from mice and the development of accurate statistical models will ultimately progress the technique for the assessment of human breast tumor margins.

show abstract

Section: Pathology Morphing and Pathology Mask Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Pulsed terahertz imaging of breast cancer in freshly excised murine tumors

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Above all methods require the feature specification, either manual or automatic, but there are some other methods which don't require any specification. 2.8 BASED ON PIXEL TRANSFORMATION M. T. Rahman et al [21] presents the morphing method based on the pixel transformation. Pixel-based morphing is achieved by replacement of pixel values followed by a simple neighboring operation.…”

Section: Multilevel Free-form Deformationmentioning

confidence: 99%

“…In Linear Morphing, linear images are segmented into lines and then transforming them according to the target image. [21]. [31].…”

Section: Linear Image Morphingmentioning

confidence: 99%

“…Feature can also be specified using line segments, curves, points and snakes [32]. Features can be automatically detected and extracted using FDNN and filters [21]. Once the features are specified the mapping between them can be obtained using bilinear mapping, spline-based mapping or free form deformation [32], triangle coordinate system [26], triangulation method [12].…”

Section: IImentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Morphing Techniques

Zope¹,

Zope²

2017

IJAEMS

View full text Add to dashboard Cite

show abstract

Polyline Morphing for Animated Schematic Maps

Forsch,

Kemna,

Langetepe

et al. 2024

J geovis spat anal

View full text Add to dashboard Cite

Thematic maps allow for the visual analysis of spatial data. When comparing two map states, preserving the mental map of a user facilitates the comparison. One way to achieve this is to use animated transitions between the states. This work presents an algorithm for computing such animations, called morphs, between schematized map objects, a technique particularly pertinent in urban mobility scenarios where schematic maps improve map legibility. In schematic maps, abstraction is used to reduce the visual complexity while still conveying information on a selected phenomenon. Our method ensures that the morph has four favorable properties: (1) it is self-intersection-free, (2) it maintains the schematization of the input features, (3) it is self-contained, and (4) every segment moves at its own constant velocity. We present an efficient algorithm to compute vertex traces and the timing of the morph. We evaluate our approach on isochrones visualizing travel times and on different layouts of schematic transit networks. The results show that the additional constraints we induce on the morphing only have a minor influence on the optimization target while they reduce the complexity of the animation.

show abstract

A novel approach of image morphing based on pixel transformation

Cited by 16 publications

References 6 publications

Pulsed terahertz imaging of breast cancer in freshly excised murine tumors

Pulsed terahertz imaging of breast cancer in freshly excised murine tumors

A Survey of Morphing Techniques

Polyline Morphing for Animated Schematic Maps

Contact Info

Product

Resources

About