paper-with-me

Papers

Memory-efficient and fast implementation of local adaptive binarization methods

2019-05-30 · Chungkwong Chan

Binarization is widely used as an image preprocessing step to separate object especially text from background before recognition. For noisy images with uneven illumination such as degraded documents, threshold values need to be computed pixel by pixel to obtain a good segmentation. Since local threshold values typically depend on moment-based statistics such as mean and variance of gray levels inside rectangular windows, integral images which are memory consuming are commonly used to accelerate the calculation. Observed that moment-based statistics as well as quantiles in a sliding window can be computed recursively, integral images can be avoided without neglecting speed, more binarization methods can be accelerated too. In particular, given a $H\times W$ input image, Sauvola's method and alike can run in $\Theta (HW)$ time independent of window size, while only around $6\min\{H,W\}$ bytes of auxiliary space is needed, which is significantly lower than the $16HW$ bytes occupied by the two integral images. Since the proposed technique enable various well-known local adaptive binarization methods to be applied in real-time use cases on devices with limited resources, it has the potential of wide application.

📄 PDF Abstract BibTeX arXiv:1905.13038

Code (1)

chungkwong/binarizer 공식 구현

Tasks

Binarization

Similar Papers 제목 키워드 기반

Progressive Stochastic Binarization of Deep Networks

2019-04-03 · David Hartmann, Michael Wand

A plethora of recent research has focused on improving the memory footprint and inference speed of deep networks by reducing the complexity of (i) numerical representations (for example, by deterministic or stochastic qu…

BinarizationNetwork PruningQuantization

Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models

2024-06-18 · Dongwon Jo, Taesu Kim, Yulhwa Kim, Jae-Joon Kim

Binarization, which converts weight parameters to binary values, has emerged as an effective strategy to reduce the size of large language models (LLMs). However, typical binarization techniques significantly diminish li…

BinarizationQuantization

Sugeno integral generalization applied to improve adaptive image binarization

2020-10-20 · Information Fusion 2020 10 · Bardozzo Francesco, De La Osa Borja, Horansk{\'a}, L'ubom{\'\i}ra 외

Classic adaptive binarization methodologies threshold pixels intensity with re-spect to adjacent pixels exploiting integral images. In turn, integral imagesare generally computed optimally by using the summed-area-table …

Binarization

Binary Graph Neural Networks

2020-12-31 · CVPR 2021 1 · Mehdi Bahri, Gaétan Bahl, Stefanos Zafeiriou

Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data. As they generalize the operations of classical CNNs on grids to arbitrary topologies, GNNs als…

BinarizationGraph Neural NetworkRepresentation Learning

Two-stage generative adversarial networks for document image binarization with color noise and background removal

2020-10-20 · Sungho Suh, Jihun Kim, Paul Lukowicz, Yong Oh Lee

Document image enhancement and binarization methods are often used to improve the accuracy and efficiency of document image analysis tasks such as text recognition. Traditional non-machine-learning methods are constructe…

BinarizationDecoderImage Enhancement