The Dahu graph-cut for interactive segmentation on 2D/3D images

Ngoc, Minh; Carlinet, Edwin; Fabrizio, Jonathan; Géraud, Thierry

doi:10.1016/j.patcog.2022.109207

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study proposed dominant color representations as a way to decrease the size of color descriptors, shifting away from histogram-based methods with numerous bins, such as the reduction to eight colors in MP7DCD (Talib et al, 2013). An approach has been proposed for treating an image as a graph with user inputs as strict constraints (Shih et al, 2016) and similarly (Ngọc et al, 2023) focuses on solving the graph-cut problem to find the minimum cut optimizing an energy function, balancing region and boundary information. To address these challenges, a proposed technique efficiently extracts the dominant color component (DCC) for optimal thresholding , which also proposed a multi-view clustering framework using K-means and graphs.…”

Section: Introductionmentioning

confidence: 99%

Dominant Color Detection For Online Fashion Retrievals

Zeybek,

Çelik

2024

Batman Üniversitesi Yaşam Bilimleri Dergisi

View full text Add to dashboard Cite

This paper introduces a novel approach aimed at efficiently extracting dominant colors from online fashion images. The method addresses challenges related to detecting overlapping objects and computationally expensive methods by combining K-means clustering and graph-cut techniques into a framework. This framework incorporates an adaptive weighting strategy to enhance color extraction accuracy. Additionally, it introduces a two-phase fashion apparel detection method called YOLOv4, which utilizes U-Net architecture for clothing segmentation to precisely separate clothing items from the background or other elements. Experimental results show that K-means with YOLOv4 outperforms K-means with the U-Net model. These findings suggest that the U-Net architecture and YOLOv4 models can be effective methods for complex image segmentation tasks in online fashion retrieval and image processing, particularly in the rapidly evolving e-commerce environment.

show abstract

Section: Introductionmentioning

confidence: 99%

Dominant Color Detection For Online Fashion Retrievals

Zeybek,

Çelik

2024

Batman Üniversitesi Yaşam Bilimleri Dergisi

View full text Add to dashboard Cite

show abstract

“…This issue has been addressed in the framework of the Image Foresting Transform (IFT) [11] with the Differential Image Foresting Transform (DIFT) [10] a WS-based and fuzzy-connected segmentation method, whose response time for interactive segmentation is proportional to size of the modified regions of the scene. Interactivity has also been addressed in the context of object segmentation with hierarchical representations, especially for trees based on threshold decomposition i.e., component trees [20] or tree of shapes [5,19].…”

Section: Introductionmentioning

confidence: 99%

Interactive Segmentation with Incremental Watershed Cuts

Lebon,

Lefèvre,

Cousty

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this article, we propose an incremental method for computing seeded watershed cuts for interactive image segmentation. We propose an algorithm based on the hierarchical image representation called the binary partition tree to compute a seeded watershed cut. We show that this algorithm fits perfectly in an interactive segmentation process by handling user interactions, seed addition or removal, in time linear with respect to the number of affected pixels. Run time comparisons with several state-of-the-art interactive and non-interactive watershed methods show that the proposed method can handle user interactions much faster than previous methods achieving significant speedup from 15 to 90, thus improving the user experience on large images.

show abstract