Closed. This question needs details or clarity. It is not currently accepting answers.
Want to improve this question? Add details and clarify the problem by editing this post.
Closed last year.
Improve this question
I have doing my research on recognize the digital numbers which is the numbers displayed on 7-segment by using camera to capture ,but ocr library has limited to it .where should I start?
SimpleCV is an open source Python framework for building computer vision applications. With it, you get access to several high-powered computer vision libraries such as OpenCV – without having to first learn about bit depths, file formats, color spaces, buffer management, eigenvalues, or matrix versus bitmap storage. This is computer vision made easy.
OpenCV is an open source computer vision and machine learning software library. OpenCV was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in the commercial products. It has C++, C, Python, Java and MATLAB interfaces and supports Windows, Linux, Android and Mac OS.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 months ago.
Improve this question
I wonder if it is possible to write a program which would limit the battery charge of a laptop. I know some manufacturers like Asus, Lenovo etc. have such build-in software, but I am curious if anyone had tried creating a universal software for that and if you would share some starting points. Not sure if that is even possible since I am unable to find such software. Thanks!
There is an almost generic tool for Linux: TLP. You find it's homepage (including a link to the source code) on https://linrunner.de/tlp/. It works as power saving utility and also can adjust the battery charge levels, BUT that feature is only for ThinkPads.
To my knowledge there is no universal interface to set the charge levels of laptop batteries, so a generic utility would have to know all that vendor specific settings probably.
A short research showed, that Linux supports more than Lenovo inside some kernel drivers, so maybe that code could help you to also write software for a different OS. My advice would be to research the possibilities for Linux to then think about a generic utility for another operating system.
Closed. This question needs details or clarity. It is not currently accepting answers.
Want to improve this question? Add details and clarify the problem by editing this post.
Closed 2 years ago.
Improve this question
My team is coordinating a system of IoT devices (which at times will run disconnected). Within these devices, we are building computer vision capabilities to further perform object tracking, multi-object identification, and picking up speech (STT).
We have determined that our models will need to 1) run locally 2) be able to run deep learning 3) be able to perform multiple tasks.
The model sizes are quite large for IoT devices, however we are examining all options in terms of determining the feasibility of the system.
Is this a problem that has come up before within the TF Lite community?
Tensorflow lite has come up with solutions for these challenges.
TensorFlow Lite for Microcontrollers and requires a 32-bit platform. It has been tested extensively with many processors based on the Arm Cortex-M Series architecture.
The following development boards are supported for IOT projects:
Arduino Nano 33 BLE Sense
SparkFun Edge
STM32F746 Discovery kit
Adafruit EdgeBadge
Adafruit TensorFlow Lite for Microcontrollers Kit
Adafruit Circuit Playground Bluefruit
Espressif ESP32-DevKitC
Espressif ESP-EYE
When it comes to running deep learning models there is already APIs available and models are trained to do object tracking and much more.
This is the link https://tfhub.dev/ where you can find pretrained models for each problem domain and run easily on the development boards mentioned above without having to think about model sizes.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 3 years ago.
Improve this question
I want to create a small application for windows that
can simulate keyboard presses and button clicks while in background
has Optical Character Recognition
I have programmed a few things in the past but never a windows application, so i don't know what language is best for that thing.
I don't need a complete Tutorial for how to do it, i just want a hint what language may be the best for it.
Greetings
Hithfaeron
Hie,
you can use any language with which you are comfortable with.
you can use c , c++ , Java , JS (Node) , python .... etc
Most of the common languages are supported in all modern OS's.
For the this you want you achieve is to make your program is to listen for keyboard and mouse events, which any programming language does by interacting with the kernel
Eventhough I don't know what you meen exactly by Optical charcter recognition you can create a windows app like that one with nearly any common language. I've actually created a .dll that is capable of simulating a keyboard at a very decent speed (up to 3000 words per minute) with visual basic. I'ts a very basic language but as I did it implementing the user32.dll library in the code it's actually very easy to use. Would you like that I shared it with you that way you don't have to worry about the coding itself as it's very tedious and repetitive.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 3 years ago.
Improve this question
I am using Yocto project to build a customized distribution to my board. I just want to ask you, what is the difference between distro features, machine features and image features ?
Yocto uses features as a means to figure out which libraries, utilities and kernel modules to include in the image.
There is some overlap between the three feature categories (especially distro- and image features), and it is not always obvious where to look for a particular feature. For example, api-documentation is a distro feature, while doc-pkgs is an image feature.
So these definitions are my own, check out the reference manual for more details.
Machine features are related to the hardware that the image is built for. For instance, the rtc feature specifies that the hardware has a built-in real-time clock, while the bluetooth feature indicates that the hardware supports bluetooth.
Distro features select broader categories of software support, though there is some overlap with machine features. Examples of distro-level features include ipv6, systemd and x11.
Image features typically (but not always, see splash or read-only-rootfs) are used to enable functionality useful for debugging and diagnosing issues. For example, allow-empty-password configures SSH servers to allow root login without password, and dbg-pkgs installs debug symbols for all packages in the image.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 7 years ago.
Improve this question
I am in my learning the landscape of Linux kernel for ARM-based SoCs development.
This is the very early stage of learning and will surely take a long time as the matters seem to be comprehensive.
The goal is to have sufficient orientation in the eco-system so as soon as concrete issues in own project are to be solved one is able to route the search/investigation in the proper trails.
There is the Linus's tree, vanilla kernel. As for ARM platform there is also the ARM port tee/project/repository. If however to have a look at MAINTAINER file there are several maintainers/sub-systems of, apparently, ARM specific narrow-spectrum topics.
I wonder why all those narrow-spectrum topics do not deliver/contribute to the ARM port (http://www.arm.linux.org.uk/) repository instead of delivering directly to Torvalds tree?
There seems to exist also ARM SUB-ARCHITECTURES sub-system. Several those narrow-spectrum sub-systems/maintainers seem to be intended for porting to certain platform, conclusion based on naming the found sub-system/maintainer. Why are these centralized at / contribute to Linus tree directly instead of doing it to ARM SUB-ARCHITECTURES sub-system or as mentioned above?
The organization is somehow mysterious, in-transparent for a newbie.