Blur image detection using Laplacian operator and Open-CV

Bansal, Raghav; Raj, Gaurav; Choudhury, Tanupriya

doi:10.1109/sysmart.2016.7894491

Cited by 108 publications

(53 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The level of weed infestation was also visually evaluated from 0 (no weeds) to 2 where many weeds were observed. The level of blurriness for each session was evaluated by calculating the average variance of the Laplacian (Bansal, Raj and Choudhury, 2016).…”

Section: Methodsmentioning

confidence: 99%

Plant detection and counting from high-resolution RGB images acquired from UAVs: comparison between deep-learning and handcrafted methods with application to maize, sugar beet, and sunflower

David

Daubige

Joudelat

et al. 2021

Preprint

View full text Add to dashboard Cite

Plants density is a key information on crop growth. Usually done manually, this task can beneficiate from advances in image analysis technics. Automated detection of individual plants in images is a key step to estimate this density. To develop and evaluate dedicated processing technics, high resolution RGB images were acquired from UAVs during several years and experiments over maize, sugar beet and sunflower crops at early stages. A total of 16247 plants have been labelled interactively. We compared the performances of handcrafted method (HC) to those of deep-learning (DL). HC method consists in segmenting the image into green and background pixels, identifying rows, then objects corresponding to plants thanks to knowledge of the sowing pattern as prior information. DL method is based on the Faster RCNN model trained over 2/3 of the images selected to represent a good balance between plant development stage and sessions. One model is trained for each crop. Results show that DL generally outperforms HC, particularly for maize and sunflower crops. The quality of images appears mandatory for HC methods where image blur and complex background induce difficulties for the segmentation step. Performances of DL methods are also limited by image quality as well as the presence of weeds. An hybrid method (HY) was proposed to eliminate weeds between the rows using the rules used for the HC method. HY improves slightly DL performances in the case of high weed infestation. A significant level of variability of plant detection performances is observed between the several experiments. This was explained by the variability of image acquisition conditions including illumination, plant development stage, background complexity and weed infestation. We tested an active learning approach where few images corresponding to the conditions of the testing dataset were complementing the training dataset for DL. Results show a drastic increase of performances for all crops, with relative RMSE below 5% for the estimation of the plant density.

show abstract

Section: Methodsmentioning

confidence: 99%

Plant detection and counting from high-resolution RGB images acquired from UAVs: comparison between deep-learning and handcrafted methods with application to maize, sugar beet, and sunflower

David

Daubige

Joudelat

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It can be seen that in addition to the rigid body component the m‐D component also induces peaks in the RT spectrum due to the partial linear‐like property of the sinusoidal curve. Thus, to make a distinction between the rigid body and m‐D signal (note the difference of steepness between rigid body peak and m‐D peaks), we utilise the Laplace operator to calculate the steepness information of the RT spectrum [8]. The expression of the Laplace operator for an image is written as

\nabla^{2} f = f false(x + 1, y false) + f false(x - 1, y false) + f false(x, y + 1 false) + f false(x, y - 1 false) - 4 f false(x, y false)

…”

Section: Radon‐laplace Methods For M‐d Removalmentioning

confidence: 99%

Micro‐Doppler effect removal in ISAR imaging based on Radon‐Laplace method

Wang

2020

Electron. lett.

View full text Add to dashboard Cite

In inverse synthetic aperture radar (ISAR) imaging, the high-resolution images can be obtained by using Range-Doppler algorithm. However, the rotational parts of the complex moving targets induce micro-Doppler (m-D) effects which influence the quality of ISAR imaging. In this Letter, a novel method of Radon-Laplace based on the Radon transform (RT) and the Laplace operator is proposed to reduce the m-D effect in ISAR imaging. For this method, the RT and Laplace operator are used to extract the rigid body parts in the short-time Fourier transform domain. Then, the rigid body parts can be got through a corresponding filter on the basis of the extraction results. The simulation and measured data results demonstrate the effectiveness of the proposed method.

show abstract

“…The world is witnessing daily a large increase in the number of digital images with the increase in digital cameras and the advancement of its technologies rapidly [12], with the widespread use of digital cameras, many users take poor quality digital photos due to a lack of experience. It is the fundamental thought in the obtaining of a blurry photo [13].…”

Section: Images Data Set Buildingmentioning

confidence: 99%

3D face creation via 2D images within blender virtual environment

Rasheed

Finjan

Hashim

et al. 2021

IJEECS

View full text Add to dashboard Cite

<p><span>Animation and virtual reality movie-making technologies are still witnessing significant progress to this day. Building and stimulating virtual characters inside these applications is a goal. Build a 3D face via using some special tools inside the virtual world is the most important part of identifying a 3D animation. Keen Tools Face Builder add-on for Blender. Interested in creating a 3D face of a famous figure, artist or the general public by adopting several 2D images added to the virtual blinder software environment. The main problem facing these tools is that they deal with high-resolution and sharpness pictures because some images that contain blurring, the result is to build a 3D face model that contains design distortions and non- clearly. in this proposed paper, build a data set for 2D pictures of a specific character (actor), at a resolution of 1920 x 1080 pixels. These images were caught by the camera, different in sharpness and blurring (four types of blurry). Using the “Laplacian Filter algorithm” and OpenCV library with Python language, to isolate blurry from sharpness 2D images. Sharpness images used to build a 3D face model that gave real and similar results to the character in the pictures. </span></p>

show abstract

Blur image detection using Laplacian operator and Open-CV

Cited by 108 publications

References 5 publications

Plant detection and counting from high-resolution RGB images acquired from UAVs: comparison between deep-learning and handcrafted methods with application to maize, sugar beet, and sunflower

Plant detection and counting from high-resolution RGB images acquired from UAVs: comparison between deep-learning and handcrafted methods with application to maize, sugar beet, and sunflower

Micro‐Doppler effect removal in ISAR imaging based on Radon‐Laplace method

3D face creation via 2D images within blender virtual environment

Contact Info

Product

Resources

About