Everything in Computer Vision, page 6
Regularization techniques for an overfitting CNN
Data augmentation expands the effective dataset, dropout prevents co-adaptation, weight decay penalizes large weights, plus early stopping and batchnorm.
Why CNNs need nonlinear activations like ReLU
ReLU introduces nonlinearity letting stacked layers model complex functions; without it any stack collapses to a single linear map.
Max pooling versus strided convolution
Pooling downsamples and adds small translation invariance with no parameters; strided conv learns its downsampling but adds parameters.
How a convolutional layer works
Learnable kernels slide over the input computing dot products, with stride controlling step size and padding controlling output size.
Stereo rectification math and its artifacts
Rectification warps both images by homographies so epipolar lines become horizontal and aligned.
The PnP problem in Structure from Motion
PnP recovers a camera's pose from known 3D points and their 2D projections; it registers new frames against the existing point cloud in SfM.
Incremental Structure from Motion pipeline
Detect and match features, estimate two-view geometry, triangulate, then incrementally add images with PnP and refine via bundle adjustment.
Fundamental matrix versus essential matrix
Both relate corresponding points across two views via the epipolar constraint; the fundamental matrix works in pixel coordinates, the essential matrix in calibrated coordinates and encodes relative pose.
Disparity and depth in stereo vision
Disparity is the horizontal shift of a point between left and right images; depth is inversely proportional to disparity given baseline and focal length.
Epipolar constraint for correspondence search
The match for p1 must lie on its epipolar line in the second image, reducing a 2D search to 1D; the relation is encoded by the fundamental matrix.
Feature choice for real-time mobile SLAM
Pick ORB for fast FAST keypoints and cheap binary descriptors matched by Hamming distance; accept reduced robustness versus SIFT for real-time, low-power operation.
CNN features for image retrieval
Pass the image through a pretrained CNN and read activations from a late layer as a descriptor; deeper layers encode semantics, earlier layers encode texture.
Bag of Visual Words model
Cluster many local descriptors (e.g. k-means) into visual words; assign each image's features to words; represent the image as a histogram of word counts for a classifier.
Descriptor matching and Lowe's ratio test
Match by nearest-neighbor descriptor distance; Lowe's ratio test keeps a match only if the best is clearly better than the second-best, rejecting ambiguous ones.
SIFT versus SURF versus ORB
SIFT is most accurate but slow with float descriptors; SURF approximates SIFT for speed; ORB is fast, binary, and free, ideal for real-time and embedded.
SIFT scale and rotation invariance
Scale-space extrema via difference-of-Gaussians give scale invariance; a dominant gradient orientation gives rotation invariance; the descriptor is a normalized gradient histogram.
Image gradients, Sobel, and Canny
The gradient measures local intensity change in x and y; Sobel approximates it via convolution kernels; Canny uses gradient magnitude and direction plus non-max suppression and hysteresis.
Harris corner detector and corner stability
Harris finds points where intensity changes strongly in all directions using the structure tensor of gradients; corners are well localized in two directions, unlike edges.
Image rotation: forward versus inverse mapping
Forward mapping sends source pixels to non-integer destinations, leaving holes and overlaps; inverse mapping iterates over output pixels, finds the source location, and interpolates.
Removing salt-and-pepper noise
Use a median filter; it replaces a pixel with the neighborhood median so extreme outliers are discarded.
We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.
See open roles