Stanford University and panel researchers P. Stone and R. Brooks et al. (2016) created the report “One Hundred Year Study on Artificial Intelligence (AI100)”. The study panel summarized the current progress and envisioned future advancements in the areas of AI and home robots as follows: AI and computer vision’s advancement led the gaming industry to surpass Hollywood as the biggest entertainment industry. Deep learning and Convolutional Neural Networks (CNNs) have enabled speech understanding and computer vision on our phones, cars, and homes. Natural Language Processing (NLP) and knowledge ..read more

A Spatial Transformer Network (STN) is an effective method to achieve spatial invariance of a computer vision system. Max Jaderberg et al. first proposed the concept in a 2015 paper by the same name. Spatial invariance is the ability of a system to recognize the same object, regardless of any spatial transformations. For example, it can identify the same car regardless of how you translate, scale, rotate, or crop its image. It even extends to various non-rigid transformations, such as elastic deformations, bending, shearing, or other distortions.   Example of how an STN maps a distorted i ..read more

AlexNet is an Image Classification model that transformed deep learning. It was introduced by Geoffrey Hinton and his team in 2012, and marked a key event in the history of deep learning, showcasing the strengths of CNN architectures and its vast applications. Before AlexNet, people were skeptical about whether deep learning could be applied successfully to very large datasets. However, a team of researchers were driven to prove that Deep Neural Architectures were the future, and succeeded in it; AlexNet exploded the interest in deep learning post-2012.   ImageNet Large Scale Visual Recog ..read more

Promptable Object Detection (POD) allows users to interact with object detection systems using natural language prompts. Thus, these systems are grounded in traditional object detection and natural language processing frameworks. Object detection systems typically use frameworks like Convolutional Neural Networks (CNNs) and Region-based CNNs (R-CNNs). In most conventional applications, the detection tasks it must perform are predefined and static.   Concept of Convolutional Neural Networks (CNN)   However, in prompt object detection systems, users dynamically direct the model with ma ..read more

Computer vision models enable the machine to extract, analyze, and recognize useful information from a set of images. Lightweight computer vision models allow the users to deploy them on mobile and edge devices. Today’s boom in CV started with the implementation of deep learning models and convolutional neural networks (CNN). The main CV methods include image classification, image localization, detecting objects, and segmentation. This article lists the most significant lightweight computer vision models SMEs can efficiently implement in their daily tasks. We’ve split the lightweight models in ..read more

Bias detection in Computer Vision (CV)  aims to find and eliminate unfair biases that can lead to inaccurate or discriminatory outputs from computer vision systems. Computer vision has achieved remarkable results, especially in recent years, outperforming humans in most tasks. Still, CV systems are highly dependent on the data they are trained on and can learn to amplify the bias within such data. Thus, it has become of utmost importance to identify bias and mitigate bias. This article will explore the key types of bias in computer vision, the techniques used to detect and mitigate them ..read more

In computer vision, image segmentation breaks down an image into distinct segments or regions for easier analysis. This technique helps precisely identify objects, boundaries, and contours, making it crucial for medical imaging, autonomous vehicles, and satellite imagery analysis. Healthcare leverages image segmentation extensively for precisely segmenting medical scans which aids in diagnosing and monitoring diseases. U-Net, a deep learning model specifically designed for biomedical image segmentation, exemplifies this. Introduced in 2015 by Olaf Ronneberger’s team, U-Net aimed to create a hi ..read more

Image segmentation task is a fundamental computer vision task that aims to partition a digital image into multiple segments or sets of pixels. These segments correspond to different objects, materials, or semantic parts of the scene.  The goal of image segmentation is to simplify and/or change the representation of an image into something more meaningful and easier to analyze. There are three main types of image segmentation: semantic segmentation, instance segmentation, and panoptic segmentation. We have put together a detailed guide on semantic and instance segmentation that you can che ..read more

Convolution is a feature extractor in image processing that extracts key characteristics and attributes from images and outputs useful image representations. CNNs learn features directly from the training data. These features can include edges, corners, textures, or other relevant attributes that aid in distinguishing an image and understanding its contents.  Object detection and image classification models later use these extracted features. Deep Learning extensively utilizes Convolutional Neural Networks (CNNs) in which convolution operations play a central role in automatic feature ext ..read more

Feature Extraction is the process of transforming raw data, often unorganized, into meaningful features, which are used to train machine learning models. In today’s digital world, machine learning algorithms are used widely for credit risk prediction, stock market forecasting, early disease detection, etc. The accuracy and performance of these models rely on the quality of the input features. In this blog, we will introduce you to feature engineering, why we need it and the different machine learning techniques available to execute it. What is Feature Extraction in Machine Learning? We provide ..read more