Facial recognition based on straight angle fuzzy texture unit matrix

Agriculture is one of the most famous case studies in deep learning. Most researchers want to detect different diseases at the early stages of cultivation to save the farmer's economy. The deep learning technique needs more data to develop an accurate system. Researchers generated more synthetic data using basic image operations in traditional approaches, but these approaches are more complicated and expensive. In deep learning and computer vision, the system's accuracy is the crucial component for deciding the system's efficiency. The model's precision is based on the image's size and quality. Getting many images from the real-world environment in medicine and agriculture is difficult. The image augmentation technique helps the system generate more images that can replicate the physical circumstances by performing various operations. It also prevents overfitting, especially when the system has fewer images than required. Few researchers experimented using CNN and simple Generative Adversarial Network (GAN), but these approaches create images with more noise. The proposed research aims to develop more data using a Meta approach. The images are processed using kernel filters. Different geometric transformations are passed as input to the enhanced GANs to reduce the noise and create more fake images using latent points, acting as weights in the neural networks. The proposed system uses random sampling techniques, passes a few processed images to the generator component of GAN, and the system uses a discriminator component to classify the synthetic data created by the Meta-Learning Approach.

Section: A Methodologies Implemented Using Researchersmentioning

confidence: 99%

Synthetic Data Augmentation of Tomato Plant Leaf using Meta Intelligent Generative Adversarial Network: Milgan

Padmanabhuni¹,

Gera²

2022

“…6 show the output of different image operations on the chilly leaves. The order of selection for these operations doesn't have any impact on the augmentation and classification process [20]. There are many image manipulation operations but the proposed system implements only five of the important operations so that the burden on the neural network gets reduced.…”

Section: ) Brightness or Contrastmentioning

confidence: 99%

Data Augmentation Techniques on Chilly Plants to Classify Healthy and Bacterial Blight Disease Leaves

Govathoti¹,

Reddy²,

Kamidi³

et al. 2022

Designing an automation system for the agriculture sector is difficult using machine learning approach. So many researchers proposed deep learning system which requires huge amount of data for training the system. The proposed system suggests that geometric transformations on the original dataset help the system to generate more images that can replicate the physical circumstances. This process is known as "Image Augmentation". This enhancement of data helps the system to produce more accurate systems in terms of all metrics. In olden days when researchers work with machine learning techniques they used to implement traditional approaches which are a time consuming and expensive process. In deep learning, most of the operations are automatically taken care by the system. So, the proposed system applies neural style and to classify the images it uses the concept of transfer learning. The system utilizes the images available in the open source repository known as "Kaggle", this majorly consists of images related to chilly, tomato and potato. But this system majorly focuses on chilly plants because it is most productive plant in the South Indian regions. Image augmentation creates new images in different scenarios using the existing images and by applying popular deep learning techniques. The model has chosen ResNet-50, which is a pretrained model for transfer learning. The advantage of using pretrained model lies in not to develop the model from scratch. This pre-trained model gives more accuracy with less number of epochs. The model has achieved an accuracy of "100%".

“…The segmentation process [22] helps find the interesting regions in the image to subtract the unwanted or uninterested parts from the original image. This process reduces the complexity as well as time to work with the image.…”

Section: A Image Pre-processing Techniquesmentioning

confidence: 99%

An Empirical Study on Fake News Detection System using Deep and Machine Learning Ensemble Techniques

Divya¹,

Banik²

2021

With the revolution that happened in electronic gadgets in the past few years, information sharing has evolved into a new era that can spread the news globally in a fraction of minutes, either through yellow media or through satellite communication without any proper authentication. At the same time, all of us are aware that with the increase of different social media platforms, many organizations try to grab people's attention by creating fake news about celebrities, politicians (or) politics, branded products, and others. There are three ways to generate fake news: tampering with an image using advanced morphing tools; this is generally a popular technique while posting phony information about the celebrities (or) cybercrimes related to women. The second one deals with the reposting of the old happenings with new fake content injected into it. For example, in generally few social media platforms either to increase their TRP ratings or to expand their subscribers, they create old news that happened somewhere years ago as latest one with new fake content like by changing the date, time, locations, and other important information and tries to make them viral across the globe. The third one deals with the image/video real happened at an event or place, but media try to change the content with a false claim instead of the original one that occurred. A few decades back, researchers started working on fake news detection topics with the help of textual data. In the recent era, few researchers worked on images and text data using traditional and ensemble deep and machine learning algorithms, but they either suffer from overfitting problems due to insufficient data or unable to extract the complex semantic relations between documents. The proposed system designs a transfer learning environment where Neural Style Transfer Learning takes care of the size and quality of the datasets. It also enhances the auto-encoders by customizing the hidden layers to handle complex problems in the real world.