Scribd
Upload
26 views5 pages

Deep Learning

The document discusses the significance of image classification in computer vision and the challenges faced by automated systems. It highlights the advantages of deep learning, including enhanced performance and cost-effectiveness, as well as its applications in self-driving cars, video games, and healthcare. Deep learning enables the extraction of useful features directly from data, improving tasks such as object detection and diagnostic accuracy.

Uploaded by

pandeyshubbhi8
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
26 views5 pages

Deep Learning

The document discusses the significance of image classification in computer vision and the challenges faced by automated systems. It highlights the advantages of deep learning, including enhanced performance and cost-effectiveness, as well as its applications in self-driving cars, video games, and healthcare. Deep learning enables the extraction of useful features directly from data, improving tasks such as object detection and diagnostic accuracy.

Uploaded by

pandeyshubbhi8
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 5

DEEP LEARNING IN

IMAGES
<SHUBBHI PANDEY>
<INTRODUCTION >

• Image classification, which can be defined as the task of categorizing


images into one of several predefined classes, is a fundamental
problem in computer vision. It forms the basis for other computer vision
tasks such as localization, detection, and segmentation. Although the
task can be considered second nature for humans, it is much more
challenging for an automated system. Some of the complications
encountered include viewpoint-dependent object variability and the
high in-class variability of having many object types. Traditionally, a
dual-stage approach was used to solve the classification problem.
Handcrafted features were first extracted from images using feature
descriptors, and these served as input to a trainable classifier.
<ADVANTAGES OF USING DEEP LEARNING>

• Rapid advancement in DL and enhancements in device capabilities


including memory capacity, computing power, power consumption,
optics, and image sensor resolution have accelerated the spread of
vision-based applications along with improved performance and cost-
effectiveness.
• Deep learning uses neural networks to learn useful representations of
features directly from data.
<EXAMPLES>

SELF-DRIVING CARS VIDEO GAMES HEALTHCARE

The AI simulates human perceptual and Helped in creating realistic character It observs hidden patterns in images
decision-making processes using deep animation, and improved game and supporting clinicians in achieving
learning and controls actions in driver design and testing. With deep diagnostic perfection. It has proven to
control systems, such as steering and
learning, game developers can create be the most effective method for organ
more engaging and immersive segmentation, cancer detection, disease
brakes. Deep learning helps in identifying
games that captivate players for categorization, and computer-assisted
the objects with high resolution pixels.
hours on end. diagnosis.
Thank You

You might also like