A Threshold Selection Method from Gray-Level Histograms

By N. Otsu. 1979

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Robust multimodal face and fingerprint fusion in the presence of spoofing attacks (2016, methodology): “The background of the image is removed using Otsu's thresholding [29] and the region of interest is automatically cropped at a dimension of 248 by 256 pixels.”
Video In Sentences Out (2012, background): “The offset is then taken to be the minimum of the value that maximizes the between-class variance (Otsu, 1979) when bipartitioning this histogram and the trained acceptance threshold offset by a fixed, but small, amount (0.4).”
Diagram Understanding in Geometry Questions (2014, methodology): “Initialize primitives: For noise removal, we apply a weak Gaussian blur on the raw image and then binarize it using Otsu’s method (Otsu 1975).”
Image Segmentation Using Deep Learning: A Survey (2020, methodology): “Numerous image segmentation algorithms have been developed in the literature, from the earliest methods, such as thresholding [4], histogram-based bundling, regiongrowing [5], k-means clustering [6], watershed methods [7], to more advanced algorithms such as active contours [8], graph cuts [9], cond”
Deep Learning for Identifying Metastatic Breast Cancer (2016, methodology): “In particular, we first transfer the original image from the RGB color space to the HSV color space, then the optimal threshold values in each channel are computed using the Otsu algorithm [16], and the final mask images are generated by combining the masks from H and S channels.”
Applying watershed algorithms to the segmentation of clustered nuclei. (1998, methodology): “The best results were obtained using the ISODATA or INTERMEANS thresholding algorithm (15).”
Identifying Purchase Intent from Social Posts (2014, methodology): “The threshold values for selecting PA and non-PA words were computed using Otsu's thresholding method (Otsu 1975).”
AUTOMATIC SEGMENTATION OF NUCLEI IN 3D MICROSCOPY IMAGES OF C.ELEGANS (2007, methodology): “After filling the hollow-shaped regions, we used Ostu’s method [6] to adaptively determine the threshold T 0 that separates the foreground pixels from the background pixels.”
Poor-prognosis colon cancer is defined by a molecularly distinct subtype and develops from serrated precursor lesions (2013, methodology): “In the DAB channel, pixels were classified as ‘stain’ using Otsu’s method[45].”
DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation (2022, methodology): “Existing classic segmentationalgorithmsare based on edge detection, thresholding, morphology, distances between two objects and pixel energy, such as Otsu thresholding [6], Snake [7] and Fuzzy algorithms [8].”
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding (2019, methodology): “Moreover, the method proposed in this paper is compared with Otsu’s thresholding method [44] with respect to pixel-level precision, recall, accuracy and F1-measure.”
Saliency Detection in the Compressed Domain for Adaptive Image Retargeting (2012, methodology): “thresholding algorithm [43] is used to binarize the energy map”
Reversible data hiding: Advances in the past two decades (2016, methodology): “Specifically, background segmentation is firstly carried out by employing Otsu’s method [142] to separate the image into background and the region of interest (ROI).”