A framework for fast automatic image cropping based on deep saliency map detection and gaussian filter

Rahman, Ziaur; Pu, Yi-Fei; Aamir, Muhammad; Ullah, Farhan

doi:10.1080/1206212x.2017.1422358

Cited by 24 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other machine learning methods for cropping focus on "salient" image regions. The basic idea is to use information learned by the CNN about where human viewers fix their gaze to center a crop around the most interesting region (Rahman et al , 2018). However, these methods are also not applicable for our understory photographs since the photographs are cluttered with no one point of interest.…”

Section: Discussionmentioning

confidence: 99%

Habitat-Net: Segmentation of habitat images using deep learning

Abrams

Vashishtha

Wong

et al. 2018

Preprint

View full text Add to dashboard Cite

Understanding environmental factors that influence forest health, as well as the occurrence and abundance of wildlife, is a central topic in forestry and ecology. However, the manual processing of field habitat data is timeconsuming and months are often needed to progress from data collection to data interpretation. Computerassisted tools, such as deeplearning applications can significantly shortening the time to process the data while maintaining a high level of accuracy. Here, we propose HabitatNet: a novel method based on Convolutional Neural Networks (CNN) to segment habitat images of tropical rainforests.HabitatNet takes color images as input and after multiple layers of convolution and deconvolution, produces a binary segmentation of the input image. We worked on two different types of habitat datasets that are widely used in ecological studies to characterize the forest conditions: canopy closure and understory vegetation. We trained the model with 800 canopy images and 700 understory images separately and then used 149 canopy and 172 understory images to test the performance of HabitatNet. We compared the performance of HabitatNet with a simple threshold based method, a manual processing by a second researcher and a CNN approach called UNet upon which HabitatNet is based.HabitatNet, UNet and simple thresholding reduced total processing time to milliseconds per image, compared to 45 seconds per image for manual processing. However, the higher mean Dice coefficient of HabitatNet (0.94 for canopy and 0.95 for understory) indicates that accuracy of HabitatNet is higher than that of both the simple thresholding (0.64, 0.83) andUNet (0.89, 0.94). HabitatNet will be of great relevance for ecologists and foresters, who need to monitor changes in their forest structures. The automated workflow not only reduces the time, it also standardizes the analytical pipeline and, thus, reduces the degree of uncertainty that would be introduced by manual processing of images by different people (either over time or between study sites). Furthermore, it provides the opportunity to collect and process more images from the field, which might increase the accuracy of the method.Although datasets from other habitats might need an annotated dataset to first train the model, the overall time required to process habitat photos will be reduced, particularly for large projects.

show abstract

Section: Discussionmentioning

confidence: 99%

Habitat-Net: Segmentation of habitat images using deep learning

Abrams

Vashishtha

Wong

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Afterward, it is designed to fetch features from a database of cropping. Using a deep learning strategy by Rahman et al [47] several images are trained to get precise importance maps by graph-based segmentation and adjustment of ray levels. To represent prominent objects, Gaussian filter and image scaling are used.…”

Section: Content-aware Croppingmentioning

confidence: 99%

A Survey on Content Aware Image Resizing Methods

Garg¹,

Negi²

2020

KSII TIIS

View full text Add to dashboard Cite

With the advancement in the field of image processing, images are being processed using various image processing algorithms. Nowadays, many efficient content-aware image resizing techniques are being used to safeguard the prominent regions and to generate better results that are visually appealing and pleasing while resizing. Advancements in the new display device with varying screen size demands the development of efficient image resizing algorithm. This paper presents a survey on various image retargeting methods, comparison of image retargeting results based on performance, and also exposes the main challenges in image retargeting such as content preservation of important regions, distortion minimization, and improving the efficiency of image retargeting methods. After reviewing literature from researchers it is suggested that the use of the single operator in image retargeting such as scaling, cropping, seam carving, and warping is not sufficient for obtaining satisfactory results, hence it is essential to combine multiple image retargeting operators. This survey is useful for the researchers interested in content-aware image retargeting.

show abstract

“…CNN is considered the correct option for this task. As a result, numerous computational models have been developed to detect visual saliency using CNN [31]. H. Misaghi et al [32] have proposed a CNN-based visual saliency method which can identify multiple salient regions to any input size.…”

Section: Visual Silence Detectionmentioning

confidence: 99%

An Optimized Architecture of Image Classification Using Convolutional Neural Network

Aamir¹,

Rahman²,

Abro³

et al. 2019

IJIGSP

Self Cite

View full text Add to dashboard Cite

The convolutional neural network (CNN) is the type of deep neural networks which has been widely used in visual recognition. Over the years, CNN has gained lots of attention due to its high capability to appropriately classifying the images and feature learning. However, there are many factors such as the number of layers and their depth, number of features map, kernel size, batch size, etc. They must be analyzed to determine how they influence the performance of network. In this paper, the performance evaluation of CNN is conducted by designing a simple architecture for image classification. We evaluated the performance of our proposed network on the most famous image repository name CIFAR-10 used for the detection and classification task. The experiment results show that the proposed network yields the best classification accuracy as compared to existing techniques. Besides, this paper will help the researchers to better understand the CNN models for a variety of image classification task. Moreover, this paper provides a brief introduction to CNN, their applications in image processing, and discuss recent advances in region-based CNN for the past few years.

show abstract

A framework for fast automatic image cropping based on deep saliency map detection and gaussian filter

Cited by 24 publications

References 32 publications

Habitat-Net: Segmentation of habitat images using deep learning

Habitat-Net: Segmentation of habitat images using deep learning

A Survey on Content Aware Image Resizing Methods

An Optimized Architecture of Image Classification Using Convolutional Neural Network

Contact Info

Product

Resources

About