> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pixeltable.com/llms.txt
> Use this file to discover all available pages before exploring further.
# vision
> 
# module pixeltable.functions.vision
Pixeltable UDFs for Computer Vision.
Example:
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
import pixeltable as pxt
from pixeltable.functions import vision as pxtv
t = pxt.get_table(...)
t.select(pxtv.draw_bounding_boxes(t.img, boxes=t.boxes, label=t.labels)).collect()
```
## func draw\_bounding\_boxes()
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
draw_bounding_boxes(
img: Image,
boxes: Json,
labels: Json | None = None,
color: String | None = None,
box_colors: Json | None = None,
fill: Bool = False,
width: Int = 1,
font: String | None = None,
font_size: Int | None = None
) -> Image
```
Draws bounding boxes on the given image.
Labels can be any type that supports `str()` and is hashable (e.g., strings, ints, etc.).
Colors can be specified as common HTML color names (e.g., 'red') supported by PIL's
[`ImageColor`](https://pillow.readthedocs.io/en/stable/reference/ImageColor.html#imagecolor-module) module or as
RGB hex codes (e.g., '#FF0000').
If no colors are specified, this function randomly assigns each label a specific color based on a hash of the label.
**Parameters:**
* **`img`** (`Image`): The image on which to draw the bounding boxes.
* **`boxes`** (`Json`): List of bounding boxes, each represented as \[xmin, ymin, xmax, ymax].
* **`labels`** (`Json | None`): List of labels for each bounding box.
* **`color`** (`String | None`): Single color to be used for all bounding boxes and labels.
* **`box_colors`** (`Json | None`): List of colors, one per bounding box.
* **`fill`** (`Bool`): Whether to fill the bounding boxes with color.
* **`width`** (`Int`): Width of the bounding box borders.
* **`font`** (`String | None`): Name of a system font or path to a TrueType font file, as required by
[`PIL.ImageFont.truetype()`](https://pillow.readthedocs.io/en/stable/reference/ImageFont.html#PIL.ImageFont.truetype).
If `None`, uses the default provided by
[`PIL.ImageFont.load_default()`](https://pillow.readthedocs.io/en/stable/reference/ImageFont.html#PIL.ImageFont.load_default).
* **`font_size`** (`Int | None`): Size of the font used for labels in points. Only used in conjunction with non-`None` `font` argument.
**Returns:**
* `Image`: The image with bounding boxes drawn on it.
## func eval\_detections()
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
eval_detections(
pred_bboxes: Json,
pred_labels: Json,
pred_scores: Json,
gt_bboxes: Json,
gt_labels: Json,
min_iou: Float = 0.5
) -> Json
```
Evaluates the performance of a set of predicted bounding boxes against a set of ground truth bounding boxes.
**Parameters:**
* **`pred_bboxes`** (`Json`): List of predicted bounding boxes, each represented as \[xmin, ymin, xmax, ymax].
* **`pred_labels`** (`Json`): List of predicted labels.
* **`pred_scores`** (`Json`): List of predicted scores.
* **`gt_bboxes`** (`Json`): List of ground truth bounding boxes, each represented as \[xmin, ymin, xmax, ymax].
* **`gt_labels`** (`Json`): List of ground truth labels.
* **`min_iou`** (`Float`): Minimum intersection-over-union (IoU) threshold for a predicted bounding box to be
considered a true positive.
**Returns:**
* `Json`: A list of dictionaries, one per label class, with the following structure:
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
{
'min_iou': float, # The value of `min_iou` used for the detections
'class': int, # The label class
'tp': list[int], # List of 1's and 0's indicating true positives for each
# predicted bounding box of this class
'fp': list[int], # List of 1's and 0's indicating false positives for each
# predicted bounding box of this class; `fp[n] == 1 - tp[n]`
'scores': list[float], # List of predicted scores for each bounding box of this class
'num_gts': int, # Number of ground truth bounding boxes of this class
}
```