Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks

Islam, Muhammad Aminul; Murray, Bryce; Buck, Andrew; Anderson, Derek T.; Scott, Grant; Popescu, Mihail; Keller, James M.

doi:10.1109/tnnls.2020.3025723

Cited by 16 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HAMO can be defined entirely in terms of erosion only. HAMO is very useful for detecting specific objects that are intended to extract such as isolated points, two connected points, three connected points, crosses, squares, triangles, ridges, corners, junctions, and so on [24][25][26][27][28].…”

Section: The Proposed Methodsmentioning

confidence: 99%

Creating Color Image Features Based on Morphology Image Processing

Abu-Faraj¹,

Alqadi²,

Zubi³

2022

View full text Add to dashboard Cite

The stage of calculating the features of digital images is considered as one of the most important stages used in the construction of recognition and discrimination systems, and the rudder of these systems depends on the values of the features obtained at this stage. In this research, we will discuss a new method for calculating the features of a digital image, regardless of its size or type. This method will be used practically morphological hit and miss operation to detect and count the appearance of certain objects in the image, and these counts will be used to form image features. The proposed method will be efficiently used to create a unique features vector for any image. The size of the features vector will be controlled by the number of structuring elements selected for each image, and for the image features database to be created the number of structuring elements that must be fixed. The proposed method will be capable of detecting any object or shape in the image, also this object must be specified by a structuring element which will be used in the hit and miss operation needed to seek for the object. It will be shown how this method will speed up the process of features extraction by decreasing the features extraction time compared with the K-means clustering method of features extraction. The selected objects can be changed, and the proposed method can be used to find the count of any selected object.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

Creating Color Image Features Based on Morphology Image Processing

Abu-Faraj¹,

Alqadi²,

Zubi³

2022

View full text Add to dashboard Cite

show abstract

“…Topological operators are applied to images by morphological operators to recover or filter out specific structures [63,64]. Mathematical morphology operators are nonlinear image operators that are based on the image spatial structure [65][66][67]. Dilation and Erosion are shape-sensitive operations that can be relatively helpful to extract discriminative spatialcontextual information during the training stage [67][68][69].…”

Section: Morphological Operation Layersmentioning

confidence: 99%

“…Mathematical morphology operators are nonlinear image operators that are based on the image spatial structure [65][66][67]. Dilation and Erosion are shape-sensitive operations that can be relatively helpful to extract discriminative spatialcontextual information during the training stage [67][68][69]. Erosion( ) and Dilation(⊕) are two basic operations in morphology operators that can be defined for a grayscale image X with size M × N and W structuring elements, as follows in Equation (4) [65,66]:…”

Section: Morphological Operation Layersmentioning

confidence: 99%

DSMNN-Net: A Deep Siamese Morphological Neural Network Model for Burned Area Mapping Using Multispectral Sentinel-2 and Hyperspectral PRISMA Images

2021

View full text Add to dashboard Cite

Wildfires are one of the most destructive natural disasters that can affect our environment, with significant effects also on wildlife. Recently, climate change and human activities have resulted in higher frequencies of wildfires throughout the world. Timely and accurate detection of the burned areas can help to make decisions for their management. Remote sensing satellite imagery can have a key role in mapping burned areas due to its wide coverage, high-resolution data collection, and low capture times. However, although many studies have reported on burned area mapping based on remote sensing imagery in recent decades, accurate burned area mapping remains a major challenge due to the complexity of the background and the diversity of the burned areas. This paper presents a novel framework for burned area mapping based on Deep Siamese Morphological Neural Network (DSMNN-Net) and heterogeneous datasets. The DSMNN-Net framework is based on change detection through proposing a pre/post-fire method that is compatible with heterogeneous remote sensing datasets. The proposed network combines multiscale convolution layers and morphological layers (erosion and dilation) to generate deep features. To evaluate the performance of the method proposed here, two case study areas in Australian forests were selected. The framework used can better detect burned areas compared to other state-of-the-art burned area mapping procedures, with a performance of >98% for overall accuracy index, and a kappa coefficient of >0.9, using multispectral Sentinel-2 and hyperspectral PRISMA image datasets. The analyses of the two datasets illustrate that the DSMNN-Net is sufficiently valid and robust for burned area mapping, and especially for complex areas.

show abstract

“…The use of the hit-or-miss transform as part of a neural network for object recognition was pioneered in [77] and some recent attempts of extending its use in the context of deep neural networks are promising [36]. However, to have robust to noise template detection [13] or the multiple ways to extend the hit-or-miss transform to grey-scale images [42,54], as well as the fact that the patterns to be matched can appear at different scales or at different rotations, yield interesting topics to be explored.…”

Section: Interpretability and "Small" Parametric Modelsmentioning

confidence: 99%

Some open questions on morphological operators and representations in the deep learning era

Angulo

2021

Preprint

View full text Add to dashboard Cite

Work on deep learning or perish": folklore wisdom in 2021.During recent years, the renaissance of neural networks as the major machine learning paradigm and more specifically, the confirmation that deep learning techniques provide state-of-the-art results for most of computer vision tasks has been shaking up traditional research in image processing. The same can be said for research in communities working on applied harmonic analysis, information geometry, variational methods, etc. For many researchers, this is viewed as an existential threat. On the one hand, research funding agencies privilege mainstream approaches especially when these are unquestionably suitable for solving real problems and for making progress on artificial intelligence. On the other hand, successful publishing of research in our communities is becoming almost exclusively based on a quantitative improvement of the accuracy of any benchmark task.

show abstract

Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks

Cited by 16 publications

References 25 publications

Creating Color Image Features Based on Morphology Image Processing

Creating Color Image Features Based on Morphology Image Processing

DSMNN-Net: A Deep Siamese Morphological Neural Network Model for Burned Area Mapping Using Multispectral Sentinel-2 and Hyperspectral PRISMA Images

Some open questions on morphological operators and representations in the deep learning era

Contact Info

Product

Resources

About