This paper presents a novel approach to automatic classifying and identifying of tree leaves using image segmentation fusion. With the development of mobile devices and remote access, automatic plant identification in images taken in natural scenes has received much attention. Image segmentation plays a key role in most plant identification methods, especially in complex background images. Wher...

In this paper, we advance the state of the art in variational image segmentation through the fusion of bottom-up segmentation and top-down classification of object behavior over an image sequence. Such an approach is beneficial for both tasks and is carried out through a joint optimization, which enables the two tasks to cooperate, such that knowledge relevant to each can aid in the resolution ...

We propose a Markov Random Field based image segmentation method which integrates domain specific information into MRF energy. The proposed segmentation method assumes that there is no labeled training set, but some priori general information referred as domain specific information about the dataset, is available. Domain specific information is received from a domain expert and formalized by a ...

This paper describes the development of the Cambridge University RT-04 diarisation system, including details of the new segmentation and clustering components. The final system gives a diarisation error rate of 23.9% on the RT-04 evaluation data, a 34% relative improvement over the RT-03s evaluation system. A further reduction down to 18.1% is shown to be possible when using the segmentation al...

Introduction: Use of SPECT/CT data is the most accurate method for patient-specific internal dosimetry when isotopes emit single gamma rays. The manual or semi-automatic segmentation of organs is a major obstacle that slows down and limits the patient-specific dosimetry. Using digital phantoms that mimic patient’s anatomy can bypass the segmentation step and facilitate the dosi...

Traditional Scene Understanding problems such as Object Detection and Semantic Segmentation have made breakthroughs in recent years due to the adoption of deep learning. However, the former task is not able to localise objects at a pixel level, and the latter task has no notion of different instances of objects of the same class. We focus on the task of Instance Segmentation which recognises an...

In this paper, we advance the state of the art in variational image segmentation through the fusion of bottom-up segmentation and top-down classification of object behavior over an image sequence. Such an approach is beneficial for both tasks and is carried out through a joint optimization, which enables the two tasks to cooperate, such that knowledge relevant to each can aid in the resolution ...

We introduce a category-independent shape prior for object segmentation. Existing shape priors assume class-specific knowledge, and thus are restricted to cases where the object class is known in advance. The main insight of our approach is that shapes are often shared between objects of different categories. To exploit this “shape sharing” phenomenon, we develop a non-parametric prior that tra...

We derive a convex optimization problem for the task of segmenting sequential data, which explicitly treats presence of outliers. We describe two algorithms for solving this problem, one exact and one a top-down novel approach, and we derive a consistency results for the case of two segments and no outliers. Robustness to outliers is evaluated on two real-world tasks related to speech segmentat...

we first describe how to “fuzzify” the estimated binary columns to create a [0,1]-valued column. werefer to this [0,1] -valued column as the soft segmentation column of the noisy spectrogram column.similarly to the collection of soft segmentation columns as the soft segmentation image, or simply asthe soft segmentation. the band-dependent posterior probability that the hard segmentation columnv...