Detecting Small Objects from Images/Videos using AI

Object detection is a technique related to Computer Vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. Small objects detection is a challenging task in computer vision due to its limited resolution and information. In this article we explore Feature Pyramid Networks for small object detection and Super Resolution GANs for data augmentation and performance improvements.

Continue Reading
Obstacle Detection on Road Using Deep Learning

Obstacle Detection on the road is an important problem and is one of the critical topics of research in Computer Vision and Deep learning. It is helpful for problems such as image annotation, pedestrian detection, face detection and various surveillance objectives. It is also deemed to play a crucial role in implementing and deploying autonomous driving on our roads and city streets in the future

Continue Reading
Visualization Tools For Time-Series Data

Time series data, available in many domains such as manufacturing (IoT) data, healthcare (patient) data, stock prices, etc. are hard to interpret simply by looking at them as they may have a lot of hidden information in terms of data trends and patterns. Data visualization helps in finding such hidden information.

Continue Reading
Medical Term Extraction from Electronic Health Reocrds (EHR)

Scientific research in the medical domain has a rich literature comprising millions of health records, clinical letters, research papers, etc. However, due to their unstructured nature, applications such as an entity extractor can help researchers and medical professionals to extract valuable information and further process them to some structured format.

Continue Reading
Capsule Networks: Basic Principles and Benefits

The 2017 idea of Dynamic Routing via Capsules, proposed by Geoffrey Hinton seems to be garnering the attention of researchers all over the world. Stated to be the next big thing in Computer Vision, find out what they are, how they work and deep dive into a simple yet useful application of the same.

Continue Reading
Entity Typing and Relation Classification for Knowledge Graph Building using ERNIE

Rich knowledge information in text can lead to better language understanding and accordingly benefits various knowledge-driven applications. To achieve this, see how ERNIE tackles two main challenges to incorporate external knowledge into language representation.

Continue Reading
Patient Knowledge Graph

Have you ever wondered how when you search for something or someone in Google search engine you see relevant stories, Wikipedia and images etc. How is all this information identified and displayed correctly? That’s the “Knowledge Graph” at work.

Continue Reading
Streaming Big Data Analytics

Processing high volumes of streaming data is a challenge, and it requires advanced BigData capabilities to manage these challenges and derive insights from this data. At AlgoAnalytics, we have developed a powerful tool that ingests real-time streaming data feeds (for example from IoT devices) to enable visualization and analytics for quicker business decisions.

Continue Reading
Enterprise Search Engine with Big Data and Deep Learning

In today’s world data is generated at a rapid pace, especially in enterprises where a vast amount of data is stored digitally. Enterprises may store data in various formats such as text, image, speech etc. While making business decisions, or even regular business transactions, it is often necessary to search and recollect specific pieces on information from this vast ocean of data. It would be a great advantage if Enterprise Search Engines [1] could search through not only the text data but also through images and speech data quickly. In order to achieve this, big data technologies can be combined with machine learning capabilities and boost search efficiency. Such Enterprise Search Engine will save both time and efforts on data search.

Continue Reading
Deep Learning using Quantum Annealers

Using D-Wave’s Quantum Annealer for pre-training of Deep Neural Networks

Despite the relentless pace of progress in computer architectures and the exponential growth in computational powers over the last few decades, there are still many problems that today’s computers can not solve. Some of these problems await the next generation of semiconductors to solve them. Others will likely remain beyond the reach of classical computers forever. The prospect of finally finding a solution to these “classically intractable” problems is setting people abuzz at the dawn of the era of Quantum Computing.

Continue Reading
Detecting Vehicle Damage using Deep Learning

With the recent advancements in Deep Learning, new applications of object detection in image processing are emerging in multiple domains. One such novel application of image analysis is detecting external damages on vehicles, for insurance as well as repair purposes. Various techniques in Deep Learning can be used to not only detect damages on automobiles (such as scratches, dents, broken glass, damaged body panels) but also to estimate the severity of damage and estimate the repair costs. The cost estimation is a critical part for the insurance industry. Such automated damage detection and cost estimation techniques can both save time (these can generate results in an instance — much faster than a manual survey and inspection process), and costs in the insurance survey process. Since one needs only the images of the damaged vehicles, such techniques can easily be used remotely, without having the surveyor visit the location of the vehicle. At AlgoAnalytics, we have our own AI model and tool developed for automated and fast damage detection.

Continue Reading
Real-Time Vehicle Tracking & Analytics using Traffic Videos

Traditional traffic monitoring systems usually include a setup based on inductive loops, RADARs, or LIDARs. However, with the increase in the number of traffic video cameras, there is a significant opportunity for Real-Time Analytics for these videos. It can provide actionable insights about traffic flow characteristics such as the location of vehicles, their tracks, and the speeds of individual vehicles. This system can further be coupled with the Automatic Number Plate Recognition (ANPR) system to find over-speeding vehicles, and automatically generate speeding tickets. It can also be coupled with the anomaly detection system to identify crashes, stalled vehicles, etc. These insights will benefit a wide variety of agencies such as the traffic control department and insurance companies.

Continue Reading
Signature Verification using Deep Learning

With the recent advancements in Deep Learning, new applications of unstructured data analytics are emerging in multiple domains. Image Analytics is one of the most common forms of unstructured data analytics. Exponential growth in text documents, images, videos in every domain is driving development of multiple image analytics applications to derive insights and enrich customer experience. Image analytics solutions play an important role in security and authentication purposes as well. One such exciting new application of Deep Learning is automated signature verification.

Continue Reading