Articles and Thoughts

Data annotation is the process of adding tags or labels to raw data such as images, videos, text, and audio. These tags form a representation of what class of objects the data belongs to and helps a machine learning model learn to identify that particular class of objects when encountered in data without a tag.
Wall crack blog photo
Cracks become a cause for concern when it comes to the safety, durability and structural integrity of building structures. When cracks develop and propagate, they tend to cause a reduction in the effective load bearing area, which, in turn, brings about an increase in stress and subsequently failure of concrete structures.
Video Processing in android featured image
OpenGL is a graphics library specification for rendering 2D and 3D graphics which achieves the required performance by using the GPU for hardware acceleration. A specification that defines APIs, implementation is the responsibility of GPU vendor. For this same reason, OpenGL APIs will behave differently on different GPUs.  
ISP featured image
Have you ever wondered how a mere smartphone takes images as impressive as your high-end DSLR camera. Even if your smartphone camera doesn’t possess physical optics, it can outperform several high-end cameras.
GIS featured image
Geographic Information System (GIS) is a computer system that analyzes and displays geographically referenced information. It uses data that is attached to a unique location. A GIS system creates, manages, analyzes, and maps various types of data. GIS connects data to a map, integrating location data (where things are) with all types of descriptive information (what things are like there).
The advancement of technology has made the 4K ultra high definition (Ultra HD) imaging the main standard for today’s multimedia products. It is now used in live sports streaming, high resolution video conferencing and even in the medical field. The high resolution provides a more immersive viewing experience and reduces blocking artefacts when viewed on a bigger screen.
Banking operations call for the processing of thousands of cheque leaves per day; this is often done in a manual fashion, consumes large amounts of time, and suffers from susceptibility to human errors. Optical Character Recognition or OCR is a technique wherein structured text is automatically interpreted by a computing system.
Railway operators must conduct routine inspections and maintenance of tracks, trains, and other equipment to ensure safe operation of railways. Through these inspection and maintenance activities, railway operators prevent service interruptions and, most importantly, reduce the chances of catastrophic railway accidents by resolving some of the more common causes of accidents, such as equipment failures, track defects, etc. 
In the current era of digital revolution, there is a growing demand for high capacity, high bandwidth, low cost, error free, low power semiconductor memories that occupies minimal area. The existing memory types and technologies are being improved further and new types and technologies are being introduced.
ANPR object detection featured image
Object detection is a task in computer vision, which requires the algorithm to predict a bounding box with a class label for each Region of Interest (ROI) in an image. Anchor-based detector have ruled this space for a long time. Recently, anchor-free detectors have started to overtake anchor-based detectors due to their lower computational complexity and efficient detections.
Telecom tower in the distance
Telecom towers are considered critical infrastructure for ensuring nation-wide communications. Telecom Service Providers rely on these towers for hosting their antennas, power modules and other communication components. To ensure uninterrupted communication services
TensorFlow Serving of AI models with Celery Workers featured image
As AI applications proliferate across industries, it is important to develop strategies to deploy these applications with high performance and at scale. With the help of Python, Celery and TensorFlow Serving, it is possible to easily deploy Machine Learning models as well as send tasks asynchronously to multiple workers using the Celery task queueing mechanism. 
SoC re-spins can mostly be attributed to functional errors that are introduced during the RTL coding phase of the design process. Hardware simulations lower the risk of such design errors. However, given the increased size and complexity of designs, simulations are slow and often do not provide enough coverage to ensure the design is bug …

Intelligent clock calibration based TDM for multi-FPGA emulation Read More »

Cobots and Vision Pose estimation for pick and stow operations
Collaborative robots or cobots are being adopted in large fulfillment centers to streamline logistics with the intent to improve efficiency right from the stage of procurement to last-mile delivery. As the global collaborative robot market is forecasted to grow at a Compound Annual Growth Rate (CAGR) of 60% by 2030 [3], cobots are paving the way for collaborative, safe and productive warehouse automation.
This article contains a more detailed treatment of backend performance optimisation considerations in platforms targeted to handle scalable AI workloads. A brief introduction of the same can be found in our blog on Use of Celery in Serverless systems for scaling AI workloads.  The platform referenced is Ignitarium’s TYQ-i® SaaS Platform (TSP), a serverless architecture …

A Hands-on Guide to Backend Performance Optimization of a SaaS platform for scalable AI workloads  Read More »

YouTube undoubtedly is the leading video streaming platform, and with the advent of new technologies from sensor, semiconductors and broadcasting technologies, the quality of video keeps improving manyfold.
Use of Celery in Serverless systems featured image
Modern SaaS deployments rely on Serverless computing, allowing software components to be scaled easily with very little management overhead. AI workload execution has also started relying heavily on this technology to allow training or serving of ML models for a variety of applications. During model serving, software components like AI models, preprocessing and postprocessing can …

Use of Celery in Serverless systems for scaling AI workloads Read More »

Image Stitching featured image
The input to image stitching is a pair of images which are treated as Train image and Query image. These two images will undergo a Registration process, which involves identifying features from the individual images. This process of image registration uses popular techniques like SIFT, ORB etc., which have been embedded in OpenCV libraries.