Quantitative analysis of coronary artery from computed tomography angiography images by Cui, Hengfei

“…An automatic coronary artery segmentation approach based on Hessian filter and connected components is proposed. …”
Get full text

Enggano flora and fauna lexicon by Wijaya, D, Rajeg, GPW, Sangian, EZ

“…The processing includes creating orthography profile and tokenisation/segmentation of the phonemic transcription, and, most importantly, creating links between the Enggano forms and their corresponding pictures (ID) to be used in the Contemporary Enggano Dictionary, which is also processed using R.…”

Discriminative learned dictionaries for local image analysis by Mairal, J, Bach, F, Ponce, J, Sapiro, G, Zisserman, A

“…This approach improves over the state of the art in texture segmentation experiments using the Brodatz database, and it paves the way for a novel scene analysis and recognition framework based on simultaneously learning discriminative and reconstructive dictionaries. …”

Deep learning-based concrete image analysis and generalization capability by Qian, Hanjie

“…To solve these problems, we propose an improved segmentation algorithm, specifically focusing on edge segmentation in SEM images, effectively enhancing the accuracy of SEM image segmentation. …”
Get full text

Electromyography signal processing based on time and time-frequency representations for prosthesis application by Mahdavi, Farzaneh Akhavan

“…In this study, it was presented that the techniques of segmentation and segment size affect the classification accuracy. …”
Get full text

Developing an Android application for medical imaging visualisation workflows by Low, Gabriel Zhi You

“…This Final Year Project focuses on the design and development of the Android application, and the integration of and improvements made to the existing frontend react web application, that allows users to view DICOM images, modify segmentation masks, and generate reports, with the aid of the existing PACS and backend server. …”
Get full text

Automated scene matching in movies by Schaffalitzky, F, Zisserman, A

“…The local spatial support of the features means that segmentation of the frame (e.g. into foreground/background) is not required, and partial occlusion is tolerated.…”

Multi-stage generative adversarial networks for generating pavement crack images by Han, Chengjia, Ma, Tao, Huyan, Ju, Tong, Zheng, Yang, Handuo, Yang, Yaowen

“…Furthermore, v2 has the additional capability of generating pavement crack images of specified types and simultaneously providing crack segmentation labels. This feature significantly enhances the practical applicability of the generated data in engineering contexts. …”
Get full text

AI based intelligent transportation system for smart nations: B by Cheng, Joey Xuan Yun

“…These results were obtained after processing of the video footages using various Image Segmentation and Image Enhancement techniques. An Automatic Incident Detection system was also built to alert users of any unusual traffic activity detected. …”
Get full text

Paint-your-mind II: stylistic image creation by concept by Wang, Anyi

“…This report presents a novel approach to generate stylistic paintings from segmentation maps. The proposed method utilizes various image-to-image translation techniques, including artistic style transfer and image enhancement, to generate visually appealing and diverse paintings. …”
Get full text

Report on industrial attachment with Autodesk Asia Private Limited by Zhu, Chenyang

“…Few projects were undertaken during the internship at Autodesk including porting Memento to Mac OS X, add check video update functionality to Memento, Mesh Segmentation using OpenCL and design and implementation of Large Mesh Web Viewer. …”
Get full text

A sparse object category model for efficient learning and complete recognition by Fergus, R, Perona, P, Zisserman, A

“…<p>We present a &ldquo;parts and structure&rdquo; model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter.</p> <p>The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. …”

A sparse object category model for efficient learning and exhaustive recognition by Fergus, R, Perona, P, Zisserman, A

“…We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. …”

Doing time : inducing temporal graphs by Bramsen, Philip James

Get full text

On efficient solution of large-size wire-grid structures in a complex environment by Lee, Yee Hui.

“…In this study, four numerical techniques (1) wavelet transform method (WTM) (2) modified fast multipole method (MFMM) (3) adaptive segmentation method (ASM) (4) weak coupling suppression method (WCSM) for the efficient solution of large-size electromagnetic (EM) problems have been studied. …”
Get full text

Colour transfer between images by Khor, Zi Yun

“…Additionally, the report will study the effectiveness of colour transfer when semantic image segmentation using a pre-trained neural network is used.…”
Get full text

The old newspaper project by Mao, Junke

“…The integrated model will perform object segmentation to extract the relevant components in the image, i.e., the headlines, embedded figures, etc, and performs OCR on these components accordingly. …”
Get full text

AiNavUT: an intelligent navigation system for unmanned tractor in airport by Zhou, Yichen

“…To improve the performance of monocular ranging, a semantic segmentation network is introduced. Navigation: based on the localization results, the costmap will be generated for the subsequent navigation.…”
Get full text

Online OCR (optical character recognition) using NVIDIA Jetson platform by Joshua Kurniawan

“…Then it seeks to explain the process of feature extraction and text segmentation. Finally, the report explains the result of OCRTesseract when multiple variable in the images is change.…”
Get full text

Object recognition and pose estimation in robotic grasping system by Zhou, Jiadong

“…Specifically, two problems addressed in the system are: i) identification and segmentation of the objects in the scene images with a fully convolutional neural network called YOLO, and ii) determination of the objects’ 6D poses by performing geometry-based methods on the point clouds. …”
Get full text