Computer Vision Software Engineer sollicitatievragen


Sollicitatievragen voor Computer Vision Software Engineer gedeeld door sollicitanten

Meest gestelde sollicitatievragen

Sorteren: Relevantie|Populair|Datum
Er werd een Software Engineer Computer Vision gevraagd...19 maart 2014

Given a 2D grid consisting of links and vacancies represented by a 2D array and assume you can move from either down (j,k)->(j+1,k) or to the right (j,k)->(j,k+1) unless there is a vacancy

4 antwoorden

Use recursion

No well defined. Is the problem to find the shortest path to the right side or bottom or shortest path to the a particular location or to connect the most locations or what? Minder

given rectangle set (overlapped or not), calculate the overlapped areas. e.g., rect{ point upperleft; width, height; } Minder

Meer reacties weergeven
Gauss Surgical

Why does one use MSE as a measure of quality. What is the scientific/mathematical reason for the same?

3 antwoorden

Mean-Square error is an error metric for measuring image or video quality it is popular video and image quality metric because the analysis and mathematics is easier with this L2-Norm metric. Most video and image quality experts will agree that MSE is not a very good measure of perceptual video and image quality. Minder

The mathematical reasoning behind the MSE is as follows: For any real applications, noise in the readings or the labels is inevitable. We generally assume this noise follows Gaussian distribution and this holds perfectly well for most of the real applications. Considering 'e' follows gaussian distribution in y=f(x) + e and calculating the MLE, we get MSE which is also L2 distance. Note: Assuming some other noise distribution may lead to other MLE estimate which will not be MSE. Minder

MSE is used for understanding the weight of the errors in any model. This helps us understand model accuracy in a way that is helpful when choosing different types of models. Check out more answers on Minder


What is meant by virtual memory? Time complexity of insertion in Linked List vs. Array? Smoothing an image - what filter to use? Salt and pepper noise removal? Memory storage - heap vs stack?

2 antwoorden

Smoothing an image can be done by convolving with a kernel: 1- a matrix of ones- simple averaging. 2- convolving with a gaussian matrix which simply means the center pixel has more weight in averaging. Salt an pepper noise: with max - min or median filters. Minder

What is meant by virtual memory? virtual memory is a memory management technique that provides an "idealized abstraction of the storage resources that are actually available on a given machine" which "creates the illusion to users of a very large (main) memory". Time complexity of insertion in Linked List vs. Array? Linked list: O(1) Array: O(n) Memory storage - heap vs stack? Stack: linear data structure, high-speed access, no fragmentation, local variables only, variables can't be resized. Heap: hierarchical data structure, slow access time(compared to stack), memory can become fragmented, global variables, variables can be resized. Minder

Oculus VR

I had a take home assignment - which you code up and bring with you to the interview for a panel discussion and presentation. I had to implement a blob detection algorithm.

1 antwoorden

Can you use the OpenCV library?


Discuss some of the object detection techniques you have worked upon

1 antwoorden

Since I had previous experience in object detection I discussed some of the techniques such as YOLO, RCNN, Fast RCNN, and Faster RCNN and how do they differ from each other. Minder


where are you from dear?

1 antwoorden

from my native place in india

Oculus VR

How would you send an encoded message in an image. First encode it, then write code to decode it.

1 antwoorden

I would always start with the simplest and fairly obvious answer; I would put the message to least significant bit layer of the image. The receiving end would only read the least significant bit layer of the image accordingly to decode the message. The least significant bit is invisible to the human eye. Test yourself by painting a rectangle with two reds next to each other of values (255,0,0) and (254,0,0). See if you can tell the difference. Minder


Check whether two words are anagram with each other.

1 antwoorden

sort strings - Check length - Compare strings - nlogn solution Efficient solution Keep a counter of each character for string 1 and a counter of each character string 2 If string lengths are different - false and if count 1 and count 2 of the character is same - they are anagrams. - Computation O(n) time. Minder

SPOT (Chile)

Exercise 1 In the popular Minesweeper game, you have a board with some mines, and those cells that don't contain a mine have a number in them that indicates the total number of mines in the neighboring cells. Starting off with some arrangements of mine we want to create a Minesweeper game setup. The execution time cannot exceed 4 seconds You're not able to import any package Exercise 2 Given a string, find out if its characters can be rearranged to form a palindrome. The execution time cannot exceed 4 seconds You're not able to import any package Example For inputString = "aabb", the output should be palindromeRearranging(inputString) = true. We can rearrange "aabb" to make "abba", which is a palindrome. Exercise 3 Write a function that reverses characters in (possibly nested) parentheses in the input string. Input strings will always be well-formed with matching ()s. Exercise 4 Given two cells on the standard chessboard, determine whether they have the same color or not. Exercise 5 In this stage, you will be using OpenCV and MTCNN. Also, this implementation runs on the top of Keras and TensorFlow. We are going to take advantage of Google Colab for these 2 last requirements because all of that comes pre-installed. In this test, we give you a cropped video of The Beatles from the song Something. Your mission consists in reading all frames of the video, doing inference in each frame, drawing in the frame the metadata, and then creating a new video from the frames processed. Using the detection from MTCNN you will be able to get face, eyes, mouth, and nose points. Also, per frame analyzed you are asked to draw-in-frame the following information of the frame: * Number of faces detected * Number of eyes, mouth and nose detected. * Number of the frame analyzed. * This information can be written at the sides of the video (you will see that the video has some black bars at the sides). * Be careful with some false positive faces! You are asked to draw only real faces. You must do a validation in which those fake faces don't appear in your drawings. You have to save all frames analyzed and then create a new video from the frames saved. You are free to create this video with any tool you want, like OpenCV, ffmpeg, GStreamer...

1 antwoorden

I presented the google colab link


Q2: You have a box that has 2 integers on input and its output is maximal and minimal values of the input. Using only this box build a system that finds median of 3 integers.

1 antwoorden

assuming we want to find the median of integers x,y,z and assume every box have the min exit and the max exit. we need to use 3 boxes: b1,b2,b3. the median= b3( b2( z , b1(x,y)->max )->min , b1(x,y)->min )->max if you draw it, it will make sense. Minder

Weergave: 1 - 10 van 52 sollicitatievragen

Glassdoor heeft 52 sollicitatievragen en verslagen van Computer vision software engineer sollicitaties. Bereid uw sollicitatiegesprek voor. Bedrijven ontdekken. Uw droombaan vinden.